persistent-memory
Skill1 starsChanged 23 days agoMITView on GitHub
Decide when a cross-session memory backend is worth adopting, then set capture, retention, redaction, and injection limits before enabling it. Use when an agent must recall decisions across sessions and the harness has no built-in memory.
9 other projects use a version of this.
Adopted by
Most recently taken up by
- yantrikos/yantrikdb-mcptheir own version, first seen Nov 2, 2026
- mthines/agent-skillstheir own version, first seen Oct 30, 2026
- edenbuilds/agentlooptheir own version, first seen Oct 13, 2026
- songjiun10-collab/Senior-thinking-skillstheir own version, first seen Oct 12, 2026
- aws-solutions/konductortheir own version, first seen Sep 23, 2026
- dbozic/claude-skillstheir own version, first seen Sep 18, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- songjiun10-collab/Senior-thinking-skills★ 87same name
- yantrikos/yantrikdb-mcp★ 25same name
- mthines/agent-skills★ 20same name
- aws-solutions/konductor★ 12same name
- rainypilgrimage/persistent-memory★ 4same name
- NullLabTests/agentkit★ 2same name
- whaojie797-design/Novera-AI-skills★ 2same name
- dbozic/claude-skills★ 1same name
- edenbuilds/agentloop★ 0same 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 repository46 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .codex/AGENTS.mdAGENTS.md
- .gemini/AGENTS.mdAGENTS.md
- .cursor/rules/agent-foundry-orchestrator.mdcCursor rule
- .cursor/rules/agent-foundry-skills.mdcCursor rule
- web/llms.txtllms.txt
- anti-slopSkill
- api-designSkill
- automation-pickSkill
- bottleneck-gatingSkill
- budget-guardSkill
- cache-identitySkill
- constraint-then-solveSkill
- context-optimizationSkill
- cron-troubleshootSkill
- e2e-test-strategySkill
- engram-routingSkill
- execution-observabilitySkill
- fallback-model-routingSkill
- feedback-loopSkill
- judge-integritySkill
- knowledge-extractSkill
- landscape-firstSkill
- measure-firstSkill
- plan-before-codeSkill
- plan-then-actSkill
- prompt-disciplineSkill
- pushback-when-wrongSkill
- quality-protocolSkill
- read-before-buildSkill
- re-verify-findingsSkill
- session-closeoutSkill
- session-distillSkill
- show-your-workSkill
- structured-output-contractSkill
- verify-firstSkill
- workflow-decomposeSkill
- agent-memory-vaultSkill
- agent-team-standardsSkill
- autonomous-briefingSkill
- book-to-skillSkill
- chrome-devtools-mcp-bridgeSkill
- design-languageSkill
- funnel-pr-guardSkill
- sql-migration-trioSkill
- token-compressionSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
4
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 31
If any answer is missing, write a handoff note instead.
- Distinctive: line 48
Start in a scratch project with a canary secret in the transcript.
- Distinctive: line 49
Verify the canary never appears in stored records or injected context.
- Distinctive: line 51
Run one session with the backend disabled to confirm work continues.
“Common” is measured: kept by at least 6 in 10 of the 8 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
Persistent Memory
Instruction-only guidance for adopting a cross-session memory backend. No memory service, hook, or database ships with this skill.
The license field records Apache-2.0 for this skill's text. Any backend you choose carries its own license and terms; check them separately.
Procedure
The decision
Adopt a backend only when all three are true:
- The harness loses context that the next session genuinely needs.
- Project docs and a short handoff note cannot carry that context.
- You can name what is captured, where it is stored, and how it is deleted.
If any answer is missing, write a handoff note instead.
What a backend must specify
| Question | Required answer |
| Capture scope | Which events: prompts, tool calls, file paths, outputs? |
| Redaction | Which patterns are removed before storage, and when? |
| Storage | Local file, local database, or remote service? Encryption at rest? |
| Retention | How long, and what triggers deletion? |
| Injection | Maximum characters or tokens added to a future prompt? |
| Failure mode | What happens when the backend is unavailable? |
| Exit | How does a user disable capture and delete existing records? |
Adoption procedure
- Record the answers above in the project's docs, not only in chat.
- Start in a scratch project with a canary secret in the transcript.
- Verify the canary never appears in stored records or injected context.
- Cap injection to the smallest useful window; review what was injected.
- Run one session with the backend disabled to confirm work continues.
- Enable it project-wide only after steps 1-5 pass.
Platform scope
Harness integrations differ and change. This repository does not certify Claude Code, Codex, Cursor, Gemini, Hermes, or OpenCode support. Check the backend's own documentation for the current adapter and test it in your environment before relying on it.
Anti-patterns
- Capturing transcripts before redaction is configured.
- Using memory as a substitute for project docs or design rationale.
- Enabling injection with no size cap or review step.
- Keeping records with no deletion path.
- Assuming a first session has history to inject.
Verification Checklist
- A canary secret was absent from storage and from injected context.
- The injection cap is configured and visibly enforced.
- Deleting records removes them from every configured store.
- A session with the backend disabled still completes.
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.

