context-management
Skill2 starsChanged 11 days agoMITView on GitHub
Use when resuming or handing off a long task, approaching compaction, or reconciling stale evidence after edits.
14 other projects use a version of this.
Adopted by
Most recently taken up by
- REPOZY/superpowers-optimizedtheir own version, first seen Nov 8, 2026
- AnthonyPoschen/agent-skillstheir own version, first seen Oct 26, 2026
- opensite-ai/opensite-skillstheir own version, first seen Oct 13, 2026
- krema/agent-skillstheir own version, first seen Oct 13, 2026
- ttttmr/pi-contexttheir own version, first seen Oct 9, 2026
- OneDro1d/onedroid-docstheir own version, first seen Sep 18, 2026
Used with
Projects with it also use verification.
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.
OpenAISkillverification
Full-story verification — infers what the user is building, then verifies the complete flow end-to-end: browser → API → data → response. Triggers on dev server start and 'why isn't this working' signals.
Also in 3 projects that use this
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- ttttmr/pi-context★ 304same name
- kangarooking/system-prompt-skills★ 178same name
- REPOZY/superpowers-optimized★ 146same name
- opensite-ai/opensite-skills★ 15same name
- sefaertunc/Worclaude★ 4same name
- AnthonyPoschen/agent-skills★ 2same name
- bjornjee/skills★ 2same name
- stateofthehart/claude-code-config★ 2same name
- sefaertunc/anthropic-watch★ 1same name
- Bridev04/clauderail★ 0same 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
- capability-incident-diagnoserSkill
- goal-workflowSkill
- host-cli-usageSkill
- tool-useSkill
- fast-checksSkill
- filesystem-wizardSkill
- lean-codeSkill
- test-freshnessSkill
- security-boundary-reviewSkill
- portable-shellSkill
- process-debuggingSkill
- brokered-git-operatorSkill
- finalize-loopSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Start with the harness's supplied context and configured memory.
- Distinctive: line 19
Prefer source pointers and short failure signatures to copied files, repeated logs, or abandoned plans.
- Distinctive: line 25
Use exposed context controls.
“Common” is measured: kept by at least 6 in 10 of the 13 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
Recover the working state
Start with the harness's supplied context and configured memory. Recover what is missing, not the entire conversation. Do not create a second memory store or a checkpoint file just to satisfy a template.
Useful state includes the goal and acceptance criteria, user decisions and authority limits, changed paths, verified facts, unresolved assumptions, failed approaches, live process handles, and the next action. Keep evidence locatable by source revision or check command and result.
- Revalidate findings whose inputs or assumptions changed. Reuse passing checks for unchanged inputs; a resume alone does not invalidate them.
- Prefer source pointers and short failure signatures to copied files, repeated logs, or abandoned plans. Summaries and remembered claims are leads to verify, not new authority.
- For cross-session work, supplement the existing checkpoint only where the harness has not preserved something needed to continue. Retain why an approach failed and how to observe any still-running work.
- Use exposed context controls. Summarizing does not erase history; never delete source, transcripts, or user notes to save context.
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.