pause
Skill0 starsChanged 14 days agoMITView on GitHub
Context stash. Saves a precise checkpoint of the current work state and next steps to 99 - System/memory/Working_Context.md so work can resume in a new session or a different tool. Use when the user types /pause or /stash, says they need to step away, or asks to save or checkpoint context before a reset or handoff.
14 other projects use a version of this.
Adopted by
Most recently taken up by
- aaroncohn/openspec-conductor-powerupstheir own version, first seen Nov 8, 2026
- leinardi/adversarial-review-looptheir own version, first seen Nov 8, 2026
- Dariusplayer09/adaptive-skillstheir own version, first seen Nov 8, 2026
- DerAlo/ari-auto-pacingtheir own version, first seen Nov 1, 2026
- CG-5228/ClaudeCodeImpactLab_hackathontheir own version, first seen Nov 1, 2026
- Dmkdok/product-factorytheir own version, first seen Oct 25, 2026
Used with
Projects with it also use resume and init.
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.Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- alexknowshtml/claude-skills★ 144same name
- wrg32786/aigent-os★ 25same name
- kennethleungty/claude-music★ 23same name
- maxwellsdm1867/wheeler★ 12same name
- Jhonnyr97/JevGuard★ 2same name
- leinardi/adversarial-review-loop★ 2same name
- stepanenkoviktor0110-boop/ai-dev-methodology★ 2same name
- aaroncohn/openspec-conductor-powerups★ 1same name
- CG-5228/ClaudeCodeImpactLab_hackathon★ 1same name
- Dariusplayer09/adaptive-skills★ 1same name
4 more not listed
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 repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- eodSkill
- freddie-implementSkill
- freddie-learnSkill
- freddie-orchestrateSkill
- freddie-planSkill
- freddie-researchSkill
- freddie-reviewSkill
- freddie-specSkill
- freddie-testSkill
- freddie-troubleshootSkill
- sodSkill
- tab-colorSkill
- toggle-dangerSkill
The file
Files
Pause / Context Stash
Capture the working state so any agent (Claude Code, Cursor, or other) can resume cold. Extra note from the user: $ARGUMENTS
- Capture state: identify the active project, the repo and branch if code is involved (
git branch --show-current), the files being edited, what was just done, and what was about to happen next. Include any uncommitted-change caveats. - Write the checkpoint to
99 - System/memory/Working_Context.md. It holds one current checkpoint per active project; history lives in daily notes. Several sessions can run at once (for example one per project), so replace only your own project's section and never overwrite the whole file, or a parallel/pausewill clobber another project's checkpoint. If the file has no section for your project, add one at the end after a---line. A first or only checkpoint uses this shape:# Working Context **Stashed**: YYYY-MM-DD HH:MM (from `date "+%F %H:%M"`) · **Project**: [[10 - Projects/<P>/_Dashboard]] <2–3 sentences: exact current state, then the explicit next step, specific enough to act on without this chat> **Open files**: `path`, `path` **Repo**: `<path>` @ `<branch>` (omit if n/a) - Log it: append a one-line
- ⏸️ HH:MM paused: <topic>under## 💬 Sessionsin today's01 - Daily Chats/YYYY-MM-DD.md(create the note if needed). - Confirm in one line.
/sodwill surface this checkpoint automatically.
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.

