task-journal
Skill0 starsChanged 5 months agoMITView on GitHub
Persistent task log across sessions: pending tasks, completed work, known issues, backlog. Use when starting a session, completing a task, hitting a blocker, or asked what is pending or in progress. Delegates session persistence to the remember plugin.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- phalbohr/skillstheir own version, first seen Oct 13, 2026
- mimoccc/my-claude-skillstheir own version, first seen Aug 1, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- mimoccc/my-claude-skills★ 1same name
- phalbohr/skills★ 1same 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 repository38 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- api-contract-validationSkill
- architecture-scannerSkill
- auto-approve-policySkill
- auto-learningSkill
- backend-patternsSkill
- branch-syncSkill
- browser-testSkill
- browseSkill
- build-checkSkill
- cache-refreshSkill
- codebase-explainerSkill
- coding-standardsSkill
- commit-styleSkill
- context-switchingSkill
- continuous-learningSkill
- db-preflightSkill
- env-preflightSkill
- eval-harnessSkill
- feature-completenessSkill
- file-indexSkill
- frontend-patternsSkill
- function-extractSkill
- idev-initSkill
- import-graphSkill
- lessons-learnedSkill
- post-creation-verifySkill
- pre-ship-verifySkill
- project-mapSkill
- self-reviewSkill
- session-resumeSkill
- skill-benchmarkSkill
- skilloptSkill
- smart-contextSkill
- strategic-compactSkill
- tdd-workflowSkill
- test-coverageSkill
- test-mapSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Write: After completing any task, encountering a blocker, or discovering a new issue
- Very specific: line 26
When the remember plugin is not installed, task-journal operates standalone using .claude/idev/task-journal/journal.md.
- Distinctive: line 141
Do NOT write to journal for trivial actions (reading files, searching)
- Distinctive: line 142
Do NOT duplicate the same entry multiple times
- Distinctive: line 143
Do NOT let the journal grow beyond ~150 lines (archive old completed items)
- Distinctive: line 144
Do NOT use the journal as a substitute for actually reading code
- Distinctive: line 145
Do NOT auto-generate backlog items — only log what the user explicitly mentions
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Task Journal Skill
Purpose
Persistent task tracking across sessions. Records what was done, what's pending, and what broke — so nothing falls through the cracks when sessions restart or context is compacted.
Activation
- Write: After completing any task, encountering a blocker, or discovering a new issue
- Read: At session start, or when user asks "what's pending?" or "what did we do?"
How It Works
Primary: remember plugin integration
The remember plugin (installed separately) handles session-level persistence via .remember/ in the project root. When available, task-journal reads from and writes alongside the remember plugin's files:
- Read at session start:
.remember/session files provide recent session history - Write task entries: Append to
.claude/idev/task-journal/journal.md(the persistent, human-curated log)
Fallback: standalone journal
When the remember plugin is not installed, task-journal operates standalone using .claude/idev/task-journal/journal.md.
Why two systems?
- remember plugin: automatic session capture, consolidation, compression — system-maintained
- task-journal: manually curated, structured task log — human-maintained for high-signal entries
- They complement each other: remember captures everything, task-journal captures what matters
Journal Format
# Task Journal
Last updated: YYYY-MM-DD HH:mm
## Active / In Progress
- [ ] [FEATURE] Task description
- File: path/to/file
- Status: what's been done so far
- Blocker: what's blocking (if any)
## Completed (Recent)
- [x] [FEATURE] Task description — YYYY-MM-DD
- Files changed: file1, file2, file3
- Summary: one-line summary of what was done
## Known Issues
- [!] [FEATURE] Issue description — YYYY-MM-DD
- File: path/to/file
- Severity: low|medium|high|critical
- Notes: debugging info, what was tried
## Backlog (User Mentioned)
- [ ] [FEATURE] Task description
- Context: what the user said about itWrite Rules
When a task is completed:
1. Move from "Active" to "Completed (Recent)"
2. Add date and files changed
3. Add one-line summaryWhen a blocker is found:
1. Add to "Known Issues" with severity
2. Update "Active" entry with blocker description
3. Include what was tried and what to check nextWhen user mentions future work:
1. Add to "Backlog" with the user's context
2. Do NOT start working on backlog items unless user asksHousekeeping:
- Keep "Completed" list to last 20 entries (archive older ones)
- Keep "Known Issues" until explicitly resolved
- Keep "Backlog" until user addresses or dismisses
- Remove duplicate entriesRead Rules
At session start:
1. Read journal.md (~50-100 lines)
2. If "Active" items exist → inform user
3. If "Known Issues" exist → mention briefly
4. Do NOT read "Completed" unless user asks for historyWhen user asks "what's pending?":
1. Show "Active" + "Known Issues" + "Backlog"
2. Exclude "Completed"When user asks "what did we do?":
1. Show "Completed (Recent)"
2. Group by date if multiple sessionsIntegration with Other Skills
Task Journal works WITH session-resume AND the remember plugin:
- session-resume = ephemeral (current session snapshot, overwritten each time)
- task-journal = persistent (rolling log across all sessions)
- remember plugin = automatic session capture and consolidation
Workflow:
1. Session starts → load session-resume (what was I doing?)
2. Session starts → load task-journal (what's the big picture?)
3. Session starts → remember plugin provides recent session history
4. Task done → update task-journal (log it)
5. Session ends → update session-resume (snapshot current state)
6. Session ends → remember plugin captures session for future referenceAnti-Patterns
- Do NOT write to journal for trivial actions (reading files, searching)
- Do NOT duplicate the same entry multiple times
- Do NOT let the journal grow beyond ~150 lines (archive old completed items)
- Do NOT use the journal as a substitute for actually reading code
- Do NOT auto-generate backlog items — only log what the user explicitly mentions
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.

