mission-swap
Skill7 starsChanged 25 days agoMITView on GitHub
Swap the dashboard hero when the owner requests it. Archive the previous mission, write the chosen replacement with a fresh slug, preserve prior checks and update the pointers.
In this repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- daily-briefSkill
- quick-captureSkill
- setupSkill
- weekly-reviewSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 16
Snapshot the old mission: Read the current dashboard/mission.json, note its slug, and copy it to archive/mission_<old-slug>.json.
- Very specific: line 18
Write the new
dashboard/mission.json: Follow schemas/mission.schema.json: - Distinctive: line 32
Keep the dashboard's single mission file and home pointers consistent with the owner's chosen focus.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Mission Swap
The dashboard hero — header, countdown, one-thing, week planner, evidence — renders entirely from dashboard/mission.json. Nothing else hardcodes the mission, so swapping it is a small, mechanical edit. This skill is the procedure; the pattern is documented in AGENTS.md.
The dashboard displays one hero mission. Swapping that slot does not decide what else the owner may pursue.
Steps
- Confirm the close. Briefly confirm the current mission is actually done (or being intentionally set down). Capture what shipped — log any outstanding wins to
06_Trackers/evidence.md(create it from06_Trackers/evidence.template.mdif it doesn't exist yet) before archiving. - Snapshot the old mission. Read the current
dashboard/mission.json, note itsslug, and copy it toarchive/mission_<old-slug>.json. If the mission had working files under01_Focus/, move them underarchive/<old-slug>/so01_Focus/is clear for the new hero. - Write the new
dashboard/mission.json. Followschemas/mission.schema.json:- Pick a fresh, unique
slug(this namespaces the week/evidence checkbox keys — a new slug guarantees old ticks don't bleed into the new mission). - Fill
hero:kicker,title,subtitle,gate(ISO 8601),gateLabel,gatePassedTitle,gatePassedMessage,mission,oneThing(tag/do/why/reframe),rule,reframeStrip. - Fill
week(theme per week, with day/week rows and theiritems) andevidence(the artifacts that will mark success).
- Pick a fresh, unique
- Preserve check history. A fresh
slugisolates the new mission's week/evidence ticks. Keep previous namespaced keys and browser backups; clearing them is unnecessary. Do not clearlocalStorageor remove other checks as part of a mission swap. - Update the pointers. So the written context matches the dashboard:
00_START_HERE.md— the "Today's hero" line (title + one main thing + gate).AGENTS.md/ project context — any "current state" note that names the active mission.
- Confirm. Show the owner the new hero line and gate, and offer to run the
daily-briefskill against the fresh mission.
Rules
- Keep the dashboard's single mission file and home pointers consistent with the owner's chosen focus.
- Validate the new
mission.jsonagainstschemas/mission.schema.jsonbefore saving. - Archive, don't delete — closed missions are the memory for the "Measure" step.
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.

