memory
Skill0 starsChanged 3 months agoMITView on GitHub
Aggressively persist facts, preferences, failures, and state so nothing is lost between sessions. Use continuously — the moment the user states a preference or correction, an approach fails, a decision lands, a phase completes, or anything surprising appears. If you wondered whether to save it, save it.
110 other projects use a version of this.
Adopted by
Most recently taken up by
- eduardoweberai-cloud/claude-skillstheir own version, first seen Nov 16, 2026
- arxdsilva/ai-loopstheir own version, first seen Nov 16, 2026
- raucheacho/lorag-claude-codetheir own version, first seen Nov 16, 2026
- matthewwong525/WongStacktheir own version, first seen Nov 15, 2026
- maxwell2732/claudecode-research-harness-workflowtheir own version, first seen Nov 15, 2026
- XORwell/archeflowtheir own version, first seen Nov 15, 2026
Used with
Projects with it also use ecosystem-reference, fractal-delegation and 10 more.
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.
naman10parikhSkillecosystem-reference
Quick-access directory of Claude Code ecosystem repos, skills, plugins, MCPs, and patterns. Use when improving the harness.
Also in 5 projects that use this
naman10parikhSkillfractal-delegation
Also in 5 projects that use this
roronoazoroshao369Skillmemory-compression
Also in 5 projects that use this
Maliot100XSkillsend-user-message
Send a proactive message to a paired user via their channel (Discord, Telegram, or WhatsApp). Use when the agent needs to notify, alert, or send an unsolicited message to a user — especially during heartbeat invocations, scheduled tasks, or when the agent wants to reach out without a prior user message in the current conversation. Triggers: 'send message to user', 'notify user', 'alert user', 'message the user on discord/telegram/whatsapp', or any need to proactively communicate with a paired sender.
Also in 4 projects that use this
jh941213Skilldocs-ci
문서 CI(링크·OpenAPI lint·breaking 게이트·mermaid 검증)나 문서 드리프트 감지(docs.yaml 신선도 검사)를 설치하거나 돌릴 때 사용. 문서 내용 작성은 docs-architecture·docs-interfaces·docs-manuals.
Also in 3 projects that use this
jh941213Skilldocs-interfaces
API·이벤트 인터페이스 문서(OpenAPI·swagger·AsyncAPI 명세, 엔드포인트 레퍼런스, API 구성도·시퀀스, API CHANGELOG)를 만들거나 코드와 맞출 때 사용. 시스템 구성도는 docs-architecture, API 설계 원칙은 api-design-principles.
Also in 3 projects that use this
- +5 more from naman10parikh
- +1 more from jh941213
Other versions110 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 110
- google-gemini/gemini-cli★ 109ksame name
- jlia0/tinyclaw★ 3.6ksame name
- TinyAGI/tinyagi★ 3.6ksame name
- TinyAGI/tinyclaw★ 3.6ksame name
- Chachamaru127/claude-code-harness★ 3.2ksame name
- codeaholicguy/ai-devkit★ 1.7ksame name
- Muuuun/luxas★ 1.2ksame name
- shobcoder/shob★ 575same name
- boshu2/agentops★ 454same name
- makushingu/harness-maxxing★ 235same name
100 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 repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- brainstormSkill
- cleanupSkill
- context-managementSkill
- critiqueSkill
- debuggingSkill
- design-decisionsSkill
- diff-managementSkill
- fan-outSkill
- final-checkSkill
- handoverSkill
- loopsSkill
- orientSkill
- planningSkill
- researchSkill
- roadmapSkill
- verificationSkill
- web-testingSkill
- writing-reviewSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 93 edited versions we read keep these.
4
Distinctive
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 30
After every write, add/update one line in memory/MEMORY.md: - name — hook.
- Distinctive: line 34
Before writing, check for an existing file that covers it — update rather than duplicate.
- Distinctive: line 37
Don't store what the repo already records (code, git history, the plans/decisions files themselves) — store pointers plus the non-obvious …
- Distinctive: line 38
Never store secrets, credentials, or sensitive personal data.
- Very specific: line 41
Read memory/MEMORY.md fully.
- Distinctive: line 44
When the index exceeds ~40 lines or feels noisy: merge duplicates, delete dead facts, cluster related entries.
“Common” is measured: kept by at least 6 in 10 of the 93 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
Memory
Bias hard toward over-writing. Redundant memory is cheap; lost context is expensive. Nothing is left unturned: if you wondered "should I save this?", the answer was yes.
Write triggers (act immediately, unprompted)
- User states a preference, correction, or way-of-working (type: user or feedback — include the WHY).
- A design decision is made (pointer to the ADR).
- An approach FAILS (record why — failure memory prevents repeated failure).
- A phase completes (state snapshot: what's done, what's next).
- Something surprising is discovered about the project, tools, or environment.
- A recurring entity appears (a person, service, convention, or constraint that will matter again).
Format
One fact per file in memory/, kebab-case name, with frontmatter:
---
name: <slug>
description: <one-line summary used for recall relevance>
type: user | feedback | project | reference | failure | decision
date: YYYY-MM-DD
---
<the fact. For feedback/failure: add **Why:** and **How to apply:** lines.
Link related memories with [[slug]].>After every write, add/update one line in memory/MEMORY.md:
- [name](file.md) — hook. The index is the recall surface — a memory missing from the index is lost.
Hygiene
- Before writing, check for an existing file that covers it — update rather than duplicate.
- Wrong memories get corrected or deleted immediately; a false memory is worse than none.
- Convert relative dates ("last week") to absolute before saving.
- Don't store what the repo already records (code, git history, the plans/decisions files themselves) — store pointers plus the non-obvious part.
- Never store secrets, credentials, or sensitive personal data.
Read protocol (Phase 0 of every task)
Read memory/MEMORY.md fully; open any entry whose description might touch the task. Memories reflect when they were written — verify stale-looking facts before relying on them.
Consolidation
When the index exceeds ~40 lines or feels noisy: merge duplicates, delete dead facts, cluster related entries. Consolidation is a real task — plan it, don't do it as a side effect.
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.

