memory-stewardship
Skill255 starsChanged 15 days agoMITView on GitHub
Maintain durable collaboration preferences, agreements and lessons when the user asks to remember, correct or stop using them, or current evidence warrants capture. Excludes temporary work, project facts, sensitive data and speculation.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- analyze-agent-codebaseSkill
- campfireSkill
- cli-operationsSkill
- diagnosing-bugsSkill
- grill-duoSkill
- grill-duo-with-docsSkill
- member-studioSkill
- review-duoSkill
- tddSkill
- worktreeSkill
- writing-for-agentsSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
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 10
Read Authority and safety to assess eligibility.
- Distinctive: line 12
Follow Read and write: inspect the complete applicable Scope, then stop, revise or add once.
- Distinctive: line 13
Before writing, apply Body and retrieval keys.
- Distinctive: line 16
Do not run an end-of-conversation Memory sweep or write several speculative candidates.
≈ “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
Memory stewardship
Preserve only information that will change future collaboration. Current instructions, facts and project authority outrank Memory. Use the user's language for Memory content and reports.
- Read Authority and safety to assess eligibility.
- Reduce the candidate to one durable understanding; select its smallest valid Scope and Kind.
- Follow Read and write: inspect the complete applicable Scope, then stop, revise or add once.
- Before writing, apply Body and retrieval keys.
- Report the actual outcome: effective, pending user review, or not written.
Do not run an end-of-conversation Memory sweep or write several speculative candidates. Deletion, deactivation, restoration and changes outside the Agent's authority require the user's Memory management controls; an opposite statement cannot simulate those actions.
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.