daily-plan
Skill509 starsChanged 3 months agoMITView on GitHub
Build today's plan from calendar, tasks, priorities and commitments, with smart scheduling suggestions. Use when the user says 'plan my day', 'what's on today', 'help me focus', or starts the morning. Also use proactively at the first session of the day. Not for reviewing a finished day; use `daily-review`.
- Reads credentials
7 other projects use a version of this.
Adopted by
Most recently taken up by
- marinvch/Cortextheir own version, first seen Nov 1, 2026
- aya-taleb/productivity-skillstheir own version, first seen Nov 1, 2026
- prsolans/claude-skillstheir own version, first seen Oct 15, 2026
- MoeenNehzati/famulustheir own version, first seen Jul 8, 2026
- talgacapri/pm-ostheir own version, first seen May 23, 2026
- nbirkner/digital-braintheir own version, first seen Apr 12, 2026
Used with
Projects with it also use weekly-review.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
QuixiAISkillweekly-review
Review the past week across goals, tasks, calendar, journal, and commitments, then propose the next week
Also in 3 projects that use this
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- MoeenNehzati/famulus★ 4same name
- aya-taleb/productivity-skills★ 1same name
- marinvch/Cortex★ 1same name
- steptian/skills★ 1same name
- nbirkner/digital-brain★ 0same name
- prsolans/claude-skills★ 0same name
- talgacapri/pm-os★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository153 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .claude/plugins/compound-engineering/CLAUDE.mdCLAUDE.md
- .cursor/rules/search-routing.mdcCursor rule
- anthropic-algorithmic-artSkill
- anthropic-brand-guidelinesSkill
- anthropic-doc-coauthoringSkill
- anthropic-docxSkill
- anthropic-frontend-designSkill
- anthropic-internal-commsSkill
- anthropic-mcp-builderSkill
- anthropic-pptxSkill
- anthropic-slack-gif-creatorSkill
- anthropic-theme-factorySkill
- anthropic-webapp-testingSkill
- anthropic-web-artifacts-builderSkill
- anthropic-xlsxSkill
- atlassian-setupSkill
- backup-nowSkill
- backup-restoreSkill
- backup-setupSkill
- calendar-setupSkill
- commitmentsSkill
- create-mcpSkill
- daily-reviewSkill
- decision-logSkill
- delegate-checkSkill
- dex-backlogSkill
- dex-doctorSkill
- dex-improveSkill
- dex-obsidian-setupSkill
- dex-rollbackSkill
- dex-updateSkill
- dex-whats-newSkill
- diff-profileSkill
- enable-semantic-searchSkill
- getting-startedSkill
- goal-backlogSkill
- google-workspace-setupSkill
- granola-setupSkill
- identity-snapshotSkill
- industry-truthsSkill
- initiative-kickoffSkill
- integrate-mcpSkill
- journalSkill
- manage-capabilitiesSkill
- meeting-closeoutSkill
- meeting-prepSkill
- ms-teams-setupSkill
- pipedrive-setupSkill
- pipeline-syncSkill
- process-meetingsSkill
- product-briefSkill
- project-healthSkill
- prompt-improverSkill
- relationship-radarSkill
- reviewSkill
- save-insightSkill
- scrapeSkill
- skill-scoreSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
55 rules. 0 are common, 24 are distinctive, and 31 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
24
Distinctive
This author's own choices. Worth a look.
31
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Run inline in the current conversation by default, so this work can see what the user has already discussed, decided, or settled this …
- Very specific: line 31
Call the Agent tool with subagent_type: "general-purpose", model: "sonnet", that prompt, and a short description.
- Distinctive: line 36
Verify it wrote the draft plan to the resolved daily-plan folder (see Daily plan folder), then run the remaining interactive steps from its …
- Very specific: line 51
Use
AGENT_INSTRUCTIONS.mdverbatim: Read the file and pass its content as the subagent prompt, substituting only the placeholders. - Very specific: line 66
Always fall back: If the subagent fails, times out, or returns nothing usable, say so plainly and run the gathering inline from the same …
- Very specific: line 94
Before executing this command, read System/user-profile.yaml → communication section and adapt tone accordingly (see CLAUDE.md → …
- Distinctive: line 100
Before gathering context, ask the session-start sweep how many meeting records are still waiting, without re-scanning the vault yourself.
- Distinctive: line 105
Ask the host for its count of waiting meeting records if it keeps one.
- Very specific: line 113
Above
0: run /process-meetings. This creates meeting notes, updates person/company pages, and extracts tasks, so the plan has complete … - Very specific: line 117
The command fails or prints nothing: treat that as unknown, not as zero: run /process-meetings as before.
- Distinctive: line 122
Check for tasks captured from phone that haven't been triaged:
- Distinctive: line 130
If items found, triage them before building the plan so task counts are accurate.
- Distinctive: line 142
Run these silently without user-facing output:
- Distinctive: line 147
Self-learning checks: Run changelog and learning review scripts if due
- Very specific: line 148
Search index refresh: Run qmd update && qmd embed to refresh vault search index with any overnight changes (meetings processed, files …
- Very specific: line 149
People index refresh: Call build_people_index from Work MCP.
- Distinctive: line 158
After background checks complete, check for noteworthy backlog activity:
- Very specific: line 160
Call list_ideas(status="active", min_score=70) from Improvements MCP
- Very specific: line 161
Check System/.synthesis-state.json for recent synthesis activity (last 7 days)
- Distinctive: line 162
If there are AI-authored or recently enriched ideas, pick the most impactful one
- Distinctive: line 171
Only show if there's genuine "Why Now?" urgency (new evidence in last 7 days)
- Distinctive: line 172
If no recent synthesis activity, skip this section entirely
- Distinctive: line 173
Never block the plan for this — it's a helpful aside, not a gate
- Very specific: line 179
If journaling.morning: true in user-profile.yaml, check for today's morning journal and prompt if missing.
- Very specific: line 185
If today is Monday and week isn't planned, offer to run /week-plan first.
- Distinctive: line 191
Check for yesterday's review and extract context (open loops, tomorrow's focus, blocked items).
- Very specific: line 273
Before commitments, read System/.dex/entity-suggestions.json (if present).
- Very specific: line 312
Check if QMD MCP tools are available by calling the status tool (QMD MCP).
- Distinctive: line 346
Check if any tasks were completed on phone since the last plan:
- Very specific: line 356
Update task status via Work MCP: update_task_status(task_title="...", status="d")
- Very specific: line 366
Check System/integrations/config.yaml for google-workspace.enabled: true.
- Distinctive: line 374
If connected and healthy:
- Very specific: line 375
Use an attention-inbox count for the headline, never a provider-wide unread total.
- Very specific: line 379
When inbox tabs are off, category:primary is empty even though the inbox has unread mail — use the inbox count.
- Very specific: line 381
Never use a provider-wide is:unread total.
- Very specific: line 398
Check System/integrations/config.yaml for teams.enabled: true.
- Distinctive: line 400
If enabled and MCP healthy:
- Distinctive: line 409
If BOTH Slack and Teams enabled:
- Distinctive: line 414
If unhealthy: skip silently (graceful degradation -- no error to user).
- Distinctive: line 424
If items found, surface:
- Very specific: line 435
Run Work MCP process_inbox_with_dedup to classify the captured items — it flags duplicates and ambiguous items and suggests a pillar.
- Very specific: line 438
Create each confirmed task via Work MCP create_task (pass due, people, or account when the captured item mentions them)
- Very specific: line 454
System health: Only when the overnight smoke report has summary.broken > 0, note that a self-check found a problem and point to /dex-doctor …
- Very specific: line 458
Read working_week.days in System/user-profile.yaml.
- Very specific: line 463
Look for notes dated that previous working day in 00-Inbox/Meetings/ (including 00-Inbox/Meetings/{date}/) and, when present, the valid …
- Distinctive: line 476
If that path is already listed, change nothing.
- Distinctive: line 496
If any, review them in one pass:
- Very specific: line 505
Unprocessed meetings: If 00-Inbox/Meetings/ has notes with unchecked ### For Me items and no tasks-extracted marker, add one line: "N …
- Very specific: line 519
Read each item: {service, external_id, title, raw}.
- Very specific: line 536
Do not pass the integration name as source.
- Very specific: line 542
Silent when empty: if inbound-tasks.json doesn't exist or is empty/[], skip this step entirely.
- Very specific: line 624
Create {daily-plan-folder}/YYYY-MM-DD.md (default 00-Inbox/Daily_Plans/YYYY-MM-DD.md):
- Distinctive: line 737
After generating the plan, push today's P0 and P1 focus tasks to Apple Reminders for native iOS notifications:
- Very specific: line 768
Call track_event with event_name daily_plan_completed and properties:
- Distinctive: line 789
No meeting context (prompt user to add manually)
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!-- Generated from `.claude/skills/daily-plan/SKILL.md` by `scripts/generate-agents-skills.py`. Do not edit. -->Execution mode
Run inline in the current conversation by default, so this work can see what the user has already discussed, decided, or settled this session. Do not fork merely because this skill was selected. Only run in the background when the user explicitly asks for a background run or the host has already obtained a specific background-work approval for this run.
Delegated gathering (large-vault scaling)
This skill stays inline as described above: it keeps session awareness, it asks the user the questions, and it owns every interactive step. What it does NOT do inline is the bulk read-gathering, which on a mature vault (hundreds of notes, thousands of indexed messages, a live calendar and multiple integrations) can be large enough to exhaust the main conversation before the useful work starts.
So the gathering phase is delegated to one general-purpose subagent via the
Agent tool, using the self-contained prompt in this skill's
AGENT_INSTRUCTIONS.md:
- Read
.agents/skills/daily-plan/AGENT_INSTRUCTIONS.md. - Substitute its placeholders (
{{TARGET_DATE}},{{TARGET_DATE_PLUS_1}},{{DAY_NAME}},{{MONTH}},{{DD}}). - Call the Agent tool with
subagent_type: "general-purpose",model: "sonnet", that prompt, and a short description. The brief is mechanical gathering, so it runs on the fast tier declared by this skill'smodel_routing.steps.data-gathering; the judgement calls stay in this conversation on the default model. - Verify it wrote the draft plan to the resolved daily-plan folder (see Daily plan folder), then run the remaining interactive steps from its findings and present the plan.
- Close out every
<!-- NEEDS TASK -->line in the draft. The subagent never creates tasks, so a focus candidate with no existing task is written without a checkbox and marked. For each one: confirm it with the user per Step 6, create the task withcreate_task, then rewrite that line as a- [ ]checkbox carrying the returned^task-YYYYMMDD-XXXanchor and remove the marker. If the user declines, remove the marker and leave the line checkbox-free. Never leave the marker in the saved plan, and never turn one of these lines into a checkbox without an anchor — an anchorless checkbox is invisible to completion sync forever (Step 6).
The subagent inherits MCP connections, runs in its own context, and that context is freed when it completes, so only its findings reach this conversation.
Use AGENT_INSTRUCTIONS.md verbatim. Read the file and pass its content as
the subagent prompt, substituting only the placeholders. Do NOT hand-write a
replacement brief from what you already know about the day: that is how steps get
silently dropped, and the omission looks complete because nothing errors. If
context from this conversation is worth adding, APPEND it to the file's content;
never substitute for it.
Two caveats that are load-bearing:
- Do not count on hooks for the subagent's writes. The hooks declared in
this skill's own frontmatter belong to this skill's run, not the subagent's,
and whether the repository-wide hooks in
the host's lifecycle settingsreach a subagent's tool calls is not something a skill should assume either way. Nothing in this skill's gathering depends on a hook; the subagent's writes must stand on their own. - Always fall back. If the subagent fails, times out, or returns nothing
usable, say so plainly and run the gathering inline from the same
AGENT_INSTRUCTIONS.md. A missing subagent must never mean a missing result.
Stays inline: the journal and Monday week-planning gates, the yesterday's review check, Dex Inbox triage, the meeting-task review and goal-link confirmations, inbound external task review, pushing focus tasks to Reminders, and usage tracking. These need the user, so they must not be delegated.
Previous-working-day notes (Step 5.10c) are gathering, not the yesterday's
review check. That step lives in AGENT_INSTRUCTIONS.md so a customization of
it reaches the subagent. The written plan must show the post-condition: notes
found for a named date/file, or none.
Purpose
Generate your daily plan with full context awareness. Automatically gathers information from your calendar, tasks, meetings, relationships, and weekly progress to create a focused plan with genuine situational awareness.
Usage
/daily-plan— Create today's daily plan/daily-plan tomorrow— Plan for tomorrow (evening planning)/daily-plan --setup— Re-run integration setup
Tone Calibration
Before executing this command, read System/user-profile.yaml → communication section and adapt tone accordingly (see CLAUDE.md → "Communication Adaptation").
Step 0: Process Unprocessed Meetings (only when something is waiting)
Before gathering context, ask the session-start sweep how many meeting records are still waiting, without re-scanning the vault yourself. The count mode prints one integer, bypasses the sweep's once-per-30-minutes notice throttle, and writes nothing, so it is safe to call every morning:
Ask the host for its count of waiting meeting records if it keeps one; if it does not, treat the count as unknown and run the meeting pass.
Branch on the answer:
0: skip this step entirely and say nothing. Yesterday evening's review already ran the catch-up pass, so on most mornings this is the answer, and re-running a full seven-day/process-meetingshere found nothing new while costing minutes.- Above
0: run/process-meetings. This creates meeting notes, updates person/company pages, and extracts tasks, so the plan has complete data. Note the count and use the extracted context in the plan. Do NOT ask for a skill rating after this sub-step — save that for the end of the full plan. - The command fails or prints nothing: treat that as unknown, not as zero:
run
/process-meetingsas before.
Step 0.5: Dex Inbox Check (Phone Captures)
Check for tasks captured from phone that haven't been triaged:
Use: reminders_list_items(list_name="Dex Inbox")If the tool is unavailable or errors (Apple Reminders phone-capture is optional and may not be set up on this machine): skip this step silently — do not surface an error for a feature the user never enabled.
If items found, triage them before building the plan so task counts are accurate. See Step 5.10a for the full triage flow.
If empty: Skip silently.
Step 0.6: Project related tasks (one ask, then never again)
Call refresh_project_related_tasks with no path. If the result is needs_opt_in, ask once using the returned ask text, then call set_project_related_tasks with their yes or no. If the result is on or off, or the tool is unavailable, skip silently. Do not write project pages by hand.
Step 1: Background Checks (Silent)
Run these silently without user-facing output:
- Release evidence: SessionStart already performs the at-most-daily bounded fetch-only check. Read its result;
do not start a second network attempt. Surface only its complete
release-appears-available-unverifiednotice, verbatim. Keepno-newer-release-observed-unverified,offline,UNKNOWN, andskippedsilent here. - Self-learning checks: Run changelog and learning review scripts if due
- Search index refresh: Run
qmd update && qmd embedto refresh vault search index with any overnight changes (meetings processed, files edited, etc.). Ifqmdis not installed, skip silently. - People index refresh: Call
build_people_indexfrom Work MCP. This keeps the People Directory current so person lookups throughout the day are fast. Takes <2 seconds. - Innovation synthesis (silent): Call
synthesize_changelog()andsynthesize_learnings()from Improvements MCP. These run in background and populate the backlog — results are surfaced in Step 1.5 below. - Granola check (silent): Granola sync uses the official API via
GRANOLA_API_KEY(environment or vault-root.env). If no key is configured, skip all Granola steps silently — an unconnected optional integration is not an error. - System health (silent): Read
System/.smoke-last-run.jsonwhen present and retain any broken-journey context for Step 5.10b.
Step 1.5: Innovation Spotlight (Concierge)
After background checks complete, check for noteworthy backlog activity:
- Call
list_ideas(status="active", min_score=70)from Improvements MCP - Check
System/.synthesis-state.jsonfor recent synthesis activity (last 7 days) - If there are AI-authored or recently enriched ideas, pick the most impactful one
Surface as a brief spotlight in the plan output (1-2 lines max):
Innovation Spotlight: Claude Code shipped native memory (v2.1.32) — this could simplify idea-006 (Session Memory MCP). Run
/dex-improve idea-006to explore.
Rules:
- Show at most 1 spotlight per daily plan (don't overwhelm)
- Rotate through ideas — don't show the same one twice in a row
- Only show if there's genuine "Why Now?" urgency (new evidence in last 7 days)
- If no recent synthesis activity, skip this section entirely
- Never block the plan for this — it's a helpful aside, not a gate
Step 2: Morning Journal Check (If Enabled)
If journaling.morning: true in user-profile.yaml, check for today's morning journal and prompt if missing.
Step 3: Monday Weekly Planning Gate
If today is Monday and week isn't planned, offer to run /week-plan first.
Step 4: Yesterday's Review Check (Soft Gate)
Check for yesterday's review and extract context (open loops, tomorrow's focus, blocked items).
Step 5: Context Gathering (ENHANCED)
Gather context from all available sources. This is where the magic happens.
5.1 Midweek Progress Check (NEW)
Use: get_week_progress()This is critical for genuine situational awareness. Extract:
- Day of week and days remaining
- Weekly priority status (complete / in_progress / not_started)
- Warnings for priorities with no activity
Surface this prominently:
"It's Wednesday. Here's where you are on this week's priorities:
- ✅ Ship pricing page — Complete (finished Monday)
- 🔄 Review proposal — In progress (2 of 5 tasks done)
- ⚠️ Customer interviews — Not started (no activity yet)
You have 2 days left this week. Priority 3 needs attention."
5.2 Calendar Capacity Analysis (NEW)
Calendar events come from the delegated gatherer. That gatherer reads
calendar.provider in System/user-profile.yaml and uses Google Workspace MCP
when the provider is google, or calendar-mcp when it is not.
Use: analyze_calendar_capacity(days_ahead=1, events=[...from the configured calendar source...])Understand the shape of today:
- Day type: stacked / moderate / open
- Meeting count and hours
- Free blocks available
- Recommendation: What kind of work fits today
Surface this:
"📅 Today's shape: Moderate (4 meetings, 3 hours total)
Free blocks:
- 8:00-9:30 AM (90 min) — Morning focus time
- 2:00-4:00 PM (120 min) — Afternoon block
Recommendation: Good for medium tasks and meeting prep. Deep work fits the 2-4pm block."
5.3 Meeting Intelligence (NEW)
For each meeting today:
Use: get_meeting_context(meeting_title="...", attendees=[...])Get genuine context, not just attendee names:
- Related project: What project is this connected to?
- Project status: What's outstanding? What's blocked?
- Outstanding tasks with attendees: What do you owe them? What do they owe you?
- Prep suggestions: What should you review before this meeting?
Surface this with surprise and delight:
"📍 Meeting: Acme Quarterly Review (2pm with Sarah Chen, Mike Ross)
Related project: Acme Implementation (Phase 2)
- Status: On track, but pricing section still in draft
- Outstanding: You owe Sarah the pricing proposal
Prep suggestion: Review proposal draft, prepare pricing options. Block 30 min before this meeting?"
5.4 Commitment Tracking (NEW)
Before commitments, read System/.dex/entity-suggestions.json (if present). If it has suggested entries, add one compact context line: "Dex suggests person pages for: X (N meetings), Y — say the word and I'll create them." This step is read-only.
Also read System/.dex/entity-cooling.json when it is present and fresh. If its consequential cold list is non-empty, surface it as one compact "❄️ Going cold" line in ## ⚠️ Heads Up; degrade silently when the feed is absent or empty, and never widen this into a vault-wide people dump.
Also read System/.dex/entity-relationships.json when it is present and fresh. If its suggestions list is non-empty, surface one compact "🔗 Relationships to confirm" line in ## ⚠️ Heads Up; degrade silently when the feed is absent, stale, or empty. Keep it as a nudge, show the page and edge being proposed, and offer the real Work MCP actions: confirm_relationship(page, edge_key) or dismiss_relationship(page, edge_key). Never choose either action without the user's per-edge say-so.
Use: get_commitments_due(date_range="today")Surface things you said you'd do:
"⚡ Commitments due today:
- You told Mike you'd get back to him by Wednesday (from Monday 1:1)
- Follow up on competitive analysis (from Acme meeting)"
5.5 Task Scheduling Suggestions (NEW)
Use: suggest_task_scheduling(include_all_tasks=False, calendar_events=[...])Match tasks to available time based on effort classification:
"📋 Scheduling suggestions:
Task Effort Suggested Time Write Q1 strategy doc Deep work (2-3h) Tomorrow (you have a 3h morning block) Review Sarah's proposal Medium (1h) Today 2-3pm (before Acme meeting) Reply to Mike Quick (15min) Between meetings ⚠️ Heads up: You have 2 deep work tasks but today's too fragmented. Consider protecting tomorrow morning."
5.6 Semantic Context Enrichment (if QMD available)
This step runs automatically when QMD is installed via /enable-semantic-search. It adds a semantic search layer on top of the standard context gathering to surface connections that keyword search misses.
Check if QMD MCP tools are available by calling the status tool (QMD MCP). If available:
- For each meeting today, run:
Surface: past discussions, related decisions, relevant commitments that share meaning but not keywords with this meeting. Example: a meeting about "customer onboarding" finds notes about "activation rates" and "time to value".query(query="[meeting topic] [attendee names]", limit=3) - For each weekly priority that's lagging, run:
Surface: vault content that advances or relates to this priority but wouldn't appear in a keyword search. Especially useful for finding forgotten context about stalled work.query(query="[priority description]", limit=3) - Cross-topic connection scan:
Surface: unexpected connections between today's meetings, tasks, and priorities. This is where semantic search shines — finding that a 2pm customer call relates to a PRD you wrote last month using completely different terminology.query(query="[today's key themes combined]", limit=5) - Merge with existing context — only add genuinely new insights. Don't duplicate what Steps 5.1-5.5 already found. Mark semantic results with their source so the plan output can distinguish them.
What this enables in the plan output:
- Meeting context sections include "Also relevant:" with thematically related past discussions
- Priority recommendations cite relevant vault content discovered by meaning
- "Heads Up" section catches connections between seemingly unrelated items
- Focus recommendations are informed by deeper vault knowledge
If QMD is not available: Skip silently. Steps 5.1-5.5 and 5.7 provide full context via standard methods.
5.7 Reminders Completion Sync (Dex Today → Dex)
Check if any tasks were completed on phone since the last plan:
Use: reminders_list_completed(list_name="Dex Today")If the tool is unavailable or errors (Apple Reminders sync is optional and may not be set up on this machine): skip this step silently — do not surface an error for a feature the user never enabled. Exception: if the tool says Reminders can't be switched on from inside VS Code, tell the user that one calm line (use the Claude app or Terminal for Reminders). Do not skip that case silently, do not advise reinstalling, and do not raise it again this session.
For each completed item:
- Match to a Dex task by title
- Update task status via Work MCP:
update_task_status(task_title="...", status="d") - Surface what was synced:
"📱 Synced from phone:
- ✅ "Follow up with Hero Coders" — marked done in Dex"
If nothing to sync: Skip silently.
5.8 Email Intelligence (if connected)
Check System/integrations/config.yaml for google-workspace.enabled: true. Also treat a
registered apple-mail-mcp server as a connected source. Before querying Apple Mail, run
python3 core/utils/doctor.py --deep --only mail.apple-search; Apple Mail search is usable
only when the mail.apple-search check reports OK / feature_status: ok. --only runs
that one probe instead of the whole live checkup (smoke journeys, search index, connected
tools), which is what a full --deep run does and what made this step slow every morning.
Google Workspace needs no local probe: its own tool response carries the health status.
If connected and healthy:
- Use an attention-inbox count for the headline, never a provider-wide unread total.
For Google Workspace, count unread in the attention inbox. Start with
is:unread category:primary. If that returns 0, confirm withis:unread in:inboxand whether any mail has the Primary label (category:primary, not only unread). When inbox tabs are off,category:primaryis empty even though the inbox has unread mail — use the inbox count. When Primary exists but has no unread, report 0. Never use a provider-wideis:unreadtotal. Use monitored labels separately to find priority messages. For Apple Mail, count unread messages in Inbox mailboxes. If the source cannot scope this reliably, omit the headline unread count. - Flag emails needing reply (> 48h since received, from key contacts in
05-Areas/People/) - Surface email threads with today's meeting attendees
Include in plan:
"Email: [X] unread in Primary/Inbox, [Y] need replies. [Z] threads with today's meeting attendees."
For Apple Mail, never interpret an empty search as "no matching mail" unless that health check
is OK. If a connected source is broken or could not be checked, do not silently skip:
include one calm "Email context omitted" line with Doctor's user_message or fix path. If the
source is not connected (OFF), omit it without noise.
5.9 Teams Intelligence (if Teams connected)
Check System/integrations/config.yaml for teams.enabled: true.
If enabled and MCP healthy:
- Get unread messages from priority channels
- Surface DMs needing response
- Check for mentions
Include in plan:
"Teams: [X] unread chats, [Y] mentions. [Z] threads with today's meeting attendees."
If BOTH Slack and Teams enabled:
- Show both digests, clearly labeled: "Slack: ..." and "Teams: ..."
- Deduplicate if the same person appears in both (merge context, label the source)
- Present side by side in the plan output under a combined "Chat Intelligence" heading
If unhealthy: skip silently (graceful degradation -- no error to user).
5.10a Mobile Capture Check (Dex Inbox)
Use: reminders_list_items(list_name="Dex Inbox")If the tool is unavailable or errors (Apple Reminders phone-capture is optional and may not be set up on this machine): skip this step silently — do not surface an error for a feature the user never enabled.
If items found, surface:
📱 Captured on phone (3 items in Dex Inbox):
- "Follow up with Peter about roadmap" — captured yesterday 4:32pm
- "Look into Rovo for in-app guides" — captured today 2:15pm
- "Send Anastasia the productized offering doc" — captured today 11:45am
Triage these now? I'll help assign pillars and priorities.
Triage flow:
- Run Work MCP
process_inbox_with_dedupto classify the captured items — it flags duplicates and ambiguous items and suggests a pillar; it does NOT create tasks - Present each item, confirm pillar with user (smart pillar inference)
- Create each confirmed task via Work MCP
create_task(passdue,people, oraccountwhen the captured item mentions them) - Mark Reminder as complete via
reminders_complete_item
If Dex Inbox is empty: Skip silently (no "0 items captured" noise).
5.10b Standard Context Gathering
Also gather:
- Calendar: Today's meetings with times and attendees
- Tasks: P0, P1, started-but-not-completed, overdue (task
Due:dates only) - People dates:
i_owe_datecan be overdue.waiting_on_dateis a wait/nudge, never overdue. A leftovernext_action_datehas no direction — do not mark it overdue. - Week Priorities: This week's Top 3
- Work Summary: Quarterly goals context (if enabled)
- People: Context for meeting attendees
- Self-Learning Alerts: Changelog updates, pending learnings
- System health: Only when the overnight smoke report has
summary.broken > 0, note that a self-check found a problem and point to/dex-doctorfor diagnosis
5.10c Previous-working-day notes
Read working_week.days in System/user-profile.yaml. Compute the previous
working day strictly before the target date (skip non-working days). If the
profile is missing or working_week.days is unusable, treat Monday-Friday as
the working week.
Look for notes dated that previous working day in 00-Inbox/Meetings/
(including 00-Inbox/Meetings/{date}/) and, when present, the valid configured
notes_folder from meeting_sources. Name the date and every file found. If
none, record that as none for that named date. Do not skip this step silently.
Person-page updates. For people mentioned in those notes, call
lookup_person. If a page exists, add the note under Recent Interactions
inside the existing <!-- dex:auto:recent-interactions --> block using:
- [{Meeting Title}]({actual vault-relative note path}) — {date}If that path is already listed, change nothing. Do not create person pages here; list people with no page for the conversation to handle. The written plan must include the post-condition: previous-working-day notes found for a named date/file, or none for that date.
5.11 Meeting-Task Review (NEW)
Give the user one place to review what their meetings turned into. Work from the
list_tasks output already gathered (open tasks include metadata_source — the
meeting note each task came from — and goal_tentative).
Recent meeting tasks. Collect open tasks whose
metadata_sourceis set and whose task ID date (^task-YYYYMMDD-…) is within the last 3 days. If any, present them compactly under the plan's context:From your meetings (3 tasks)
- Send Acme the revised pricing — from Acme Quarterly Review (due Jul 15)
- …
Tentative goal links. Collect open tasks where
goal_tentativeis true. If any, review them in one pass:2 tasks have a likely goal link marked (?) — want to confirm them?
- "Draft churn playbook" → Q3-2026-goal-2: Reduce churn to 4% — keep this link?
For each answer, call Work MCP
confirm_goal_link(task_id, "confirm")to keep the link orconfirm_goal_link(task_id, "clear")to remove it. Never edit the task file by hand for this.- Unprocessed meetings. If
00-Inbox/Meetings/has notes with unchecked### For Meitems and notasks-extractedmarker, add one line: "N meetings have unextracted action items — run/process-meetingsto turn them into tasks."
Skip this entire step silently when nothing qualifies — no "0 tasks from meetings" noise.
5.12 Inbound External Tasks Review (NEW)
Give the user one place to review tasks that arrived from a connected task app
(Todoist / Things / Trello) since the last sync. Check
System/integrations/inbound-tasks.json. If it exists and is non-empty:
- Read each item:
{service, external_id, title, raw}. Therawobject contains the service payload and may include notes/description, priority, and an inferredpillar. - For each, offer a one-line summary and ask whether to bring it into Dex:
📥 From [service]: "[title]" Import as a Dex task? (yes / skip / [pillar] [priority]) - On confirmation (or pillar/priority provided), call
create_taskwith:title: from the itemon_duplicate: "fail"(skip if already exists)pillar: user-specified, otherwiseraw.pillar(the sync step fills this in from an automatic pillar guess when inference succeeds). If it is absent, ask the user to choose a valid pillar before callingcreate_taskpriority: user-specified, otherwise a valid P0-P3 value fromrawwhen presentcontext: notes/description/context fromrawwhen presentexternal_service: the item'sserviceexternal_id: the item'sexternal_id- Do not pass the integration name as
source;sourceis reserved for a vault-relative source page, while the external mapping records provenance - Passing both external fields makes task creation and mapping one operation, so a sync cannot push the newly accepted task back to the originating service
- On "skip": leave the item in the queue so it can be reviewed later
Silent when empty: if inbound-tasks.json doesn't exist or is empty/[], skip this
step entirely. Never say "no inbound tasks" — just proceed.
Step 6: Synthesis
Combine all gathered context into actionable recommendations:
Focus Recommendation
Generate 3 recommended focus items based on:
- P0 tasks (highest weight)
- Weekly priority alignment (especially lagging priorities!)
- Meeting prep needs
- Commitments due
The system should actively recommend, not just list:
"Based on your week progress and today's shape, I recommend focusing on:
- Prep for Acme meeting — Priority 2 is lagging and this meeting is critical
- Reply to Mike — Commitment due today
- Task X from Priority 1 — Keeps momentum on your shipped priority"
Task IDs are mandatory on focus items (completion sync depends on them):
Completion sync (Work MCP update_task_status, which updates every file the task
appears in) only finds a line if that single line contains BOTH a - [ ] / - [x]
checkbox AND the task's ^task-YYYYMMDD-XXX anchor. A focus item written without the ID — or with the ID on
a different line — is invisible to sync: ticking the task done in Tasks.md never
updates the plan, and marking the plan item done never updates Tasks.md.
So, for each recommended focus item:
- If it maps to an existing Tasks.md task (search by title/keywords), you MUST
write it in the plan as a
- [ ]checkbox line with that task's^task-YYYYMMDD-XXXanchor at the end of the same line. Never omit the ID, never put it on its own line. - If it's real work with no Tasks.md entry yet, create the task first via Work MCP
create_task, then embed the returned task ID the same way. - Only if it isn't a task at all (e.g. "protect the 2-4pm free block") may the line omit an ID — and then it gets no checkbox either, so it can't masquerade as a syncable task.
Format notes that matter: use - [ ] (dash checkbox), not 1. [ ] — numbered
checkboxes do not contain the literal - [ ] string the sync matcher looks for, so
they never sync even with an ID present.
Meeting Prep (Enhanced)
For each meeting, show:
- Who's attending + People/ context
- Related project status
- Outstanding tasks with attendees
- Suggested prep time and what to prepare
Heads Up (Enhanced)
Flag potential issues:
- Weekly priorities with no activity (midweek warning)
- Commitments due today
- Back-to-back meetings
- P0 items with no time blocked
- Deep work tasks with no suitable slot this week
- Invitees who have not accepted — never the organiser. Calendar APIs often leave
the organiser as Pending, Unknown, or needsAction. Treat
is_organizer: true, Googleorganizer: true/organizer.emailmatching that person, and the user themselves when they organised the meeting (is_current_user/selfplus organiser) as having accepted. Do not write "has not accepted" for them.
Step 7: Generate Daily Plan
ALWAYS generate and save a new plan file. Never skip generation because a plan from a previous day exists in the conversation or vault. Even if context from a prior plan is visible, today is a new day and requires its own plan. If a plan for today's date already exists, overwrite it (the user is requesting a refresh).
Filling in {{^task-id}} in Today's Focus: replace it with the item's real
^task-YYYYMMDD-XXX anchor per the Task IDs rule in Step 6 (mandatory whenever the
item maps to a Tasks.md task — create the task first if needed). If the item is not a
task at all, drop both the placeholder and the - [ ] checkbox for that line.
Daily plan folder. Default for a new vault is 00-Inbox/Daily_Plans/. If System/folder-paths.yaml has daily_plans:, write there. If dated YYYY-MM-DD.md daily plans already live in one other folder, keep using that folder — do not move those files and do not start a second copy in the inbox. New vaults with no existing plans use 00-Inbox/Daily_Plans/.
Create {daily-plan-folder}/YYYY-MM-DD.md (default 00-Inbox/Daily_Plans/YYYY-MM-DD.md):
---
date: YYYY-MM-DD
type: daily-plan
integrations_used: [calendar, tasks, people, work-intelligence]
---
# Daily Plan — {{Day}}, {{Month}} {{DD}}
## TL;DR
- {{1-2 sentence summary including week progress}}
- {{X}} meetings today, day is {{stacked/moderate/open}}
- {{Key focus area based on week priorities}}
---
## 📊 Week Progress (Midweek Check)
**Day {{X}} of 5** — {{days_remaining}} days left this week
| Priority | Status | Notes |
|----------|--------|-------|
| {{Priority 1}} | ✅ Complete | Finished {{day}} |
| {{Priority 2}} | 🔄 In progress | {{X}} of {{Y}} tasks done |
| {{Priority 3}} | ⚠️ Not started | Needs attention |
**This week's focus:** {{Recommendation based on lagging priorities}}
---
## 📅 Today's Shape
**Day type:** {{stacked/moderate/open}} ({{X}} meetings, {{Y}} hours)
**Free blocks:**
- {{Time range}}: {{Size}} — {{Recommended use}}
**Best for:** {{Quick tasks only / Medium tasks / Deep work opportunity}}
---
## ⚡ Commitments Due Today
- [ ] {{Commitment}} — from {{source}}
- [ ] {{Commitment}} — from {{source}}
---
## 🎯 Today's Focus
**If I only do three things today:**
- [ ] {{Focus item 1}} — {{Pillar}} *(supports Week Priority #X)* {{^task-id}}
- [ ] {{Focus item 2}} — {{Pillar}} *(supports Week Priority #Y)* {{^task-id}}
- [ ] {{Focus item 3}} — {{Pillar}} {{^task-id}}
---
## 📍 Meetings (with Context)
### {{Time}} — {{Meeting Title}}
**Attendees:** {{Names}}
**Related project:** {{Project name}} ({{status}})
**Outstanding with them:**
- {{Task/commitment}}
**Prep needed:** {{What to review/prepare}}
**Suggested prep time:** {{Block X min before}}
---
### {{Time}} — {{Meeting Title}}
[Repeat for each meeting]
---
## 📋 Task Scheduling
| Task | Effort | Suggested Slot | Reason |
|------|--------|----------------|--------|
| {{Task}} | Deep work | {{Day/time}} | {{Reason}} |
| {{Task}} | Medium | {{Day/time}} | {{Reason}} |
| {{Task}} | Quick | Between meetings | Batch these |
{{If deep work capacity warning}}
> ⚠️ You have {{X}} deep work tasks but only {{Y}} suitable slots this week. Consider protecting time or deferring.
---
## ⚠️ Heads Up
- {{Previous-working-day notes: found YYYY-MM-DD `path` / none for YYYY-MM-DD}}
- {{❄️ Going cold: consequential people/accounts from the cooling feed, when present}}
- {{🔗 Relationships to confirm: suggested typed relationships from the feed, when present}}
- {{Warning about lagging weekly priority}}
- {{Commitment due today}}
- {{Back-to-back meetings}}
- {{Other flags}}
---
*Generated: {{timestamp}}*
*Week progress: {{X}}/{{Y}} priorities on track*Step 7.5: Push Focus Tasks to Reminders (Dex → iPhone)
After generating the plan, push today's P0 and P1 focus tasks to Apple Reminders for native iOS notifications:
- Clear yesterday's items:
Use: reminders_clear_completed(list_name="Dex Today") - Push today's focus items:
For each P0/P1 task in today's focus:
Use: reminders_create_item( list_name="Dex Today", title="Task title", notes="From Dex daily plan", due_date="YYYY-MM-DD" ) - Confirm silently:
"📱 Pushed 3 focus tasks to iPhone Reminders (Dex Today)"
If the tool is unavailable or errors: Skip silently — do not surface an error for a feature the user never enabled. Exception: if the tool says Reminders can't be switched on from inside VS Code, tell the user that one calm line (use the Claude app or Terminal for Reminders). Do not skip that case silently, do not advise reinstalling, and do not raise it again this session.
Step 8: Track Usage (Silent)
Call the mark_feature_used tool on the dex-analytics MCP server with daily-plan. This ticks the feature's box in System/usage_log.md, which is what /dex-level-up reads to recommend features that have not been tried. It writes locally and sends nothing, so it runs whether or not analytics is enabled.
Analytics (Silent):
Call track_event with event_name daily_plan_completed and properties:
meetings_count: number of meetings todaytasks_surfaced: number of tasks shownpriorities_count: number of priorities
This only fires if the user has opted into analytics. No action needed if it returns "analytics_disabled".
Graceful Degradation
For MCP responses, follow CLAUDE.md's feature_status rendering convention before applying these fallbacks.
The plan works at multiple levels:
Full Context (All MCPs available)
- Complete week progress, meeting intelligence, scheduling suggestions
- Maximum "surprise and delight"
Partial Context (Work MCP only)
- Week progress and task scheduling
- No meeting context (prompt user to add manually)
Minimal Context (No MCPs)
- Interactive flow asking about priorities
- Basic daily note
MCP Dependencies (Updated)
| Integration | MCP Server | Tools Used |
| Calendar | calendar-mcp, or google-workspace-mcp when calendar.provider is google | Apple: calendar_get_today, calendar_get_events_with_attendees. Google: list_calendars, get_events |
| Reminders | calendar-mcp | reminders_list_items, reminders_complete_item, reminders_create_item, reminders_ensure_lists, reminders_list_completed, reminders_find_and_complete, reminders_clear_completed |
| Granola | granola-mcp | granola_get_recent_meetings |
| Work | work-mcp | list_tasks, get_week_progress, get_meeting_context, get_commitments_due, analyze_calendar_capacity, suggest_task_scheduling |
| Improvements | dex-improvements-mcp | synthesize_changelog, synthesize_learnings, list_ideas |
| Google Workspace | google-workspace-mcp | Gmail query, email search (if enabled) |
| Apple Mail | apple-mail-mcp | Local full-text mail search (only after mail.apple-search is healthy) |
| Teams | teams-mcp | teams_list_chats, teams_search_messages, teams_health_check (if enabled) |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

