memory-hygiene
Skill0 starsChanged 5 months agoMITView on GitHub
Use when deciding what to remember and where to store it, to keep Christian's two memory systems clean and non-overlapping. Triggers on 'remember this', 'save this for later', end-of-session handoffs, or when a durable fact emerges. Decides Obsidian vault vs ~/.claude auto-memory vs ~/.remember buffer, dedups against existing memories, and writes in the correct format.
11 other projects use a version of this.
Adopted by
Most recently taken up by
- BSSE23047/nauraiz-devtheir own version, first seen Nov 8, 2026
- mahsumaktas/agent-evolution-kittheir own version, first seen Nov 8, 2026
- HsuanYuLee/polaristheir own version, first seen Nov 5, 2026
- Kein-chronicle/claude-code-memory-linttheir own version, first seen Nov 1, 2026
- GH-Mason/agent-memory-disciplinetheir own version, first seen Sep 24, 2026
- NecturaLabs/AgentSkillstheir own version, first seen Sep 24, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- huytieu/COG-second-brain★ 1.3ksame name
- NUX-Design/claude-skills-fable-opus★ 24same name
- HsuanYuLee/polaris★ 5same name
- megandmartin/agent-skills-repo★ 3same name
- BSSE23047/nauraiz-dev★ 2same name
- mahsumaktas/agent-evolution-kit★ 2same name
- NecturaLabs/AgentSkills★ 1same name
- NITISH-R-G/agent-memory-protocol★ 1same name
- GH-Mason/agent-memory-discipline★ 0same name
- Kein-chronicle/claude-code-memory-lint★ 0same name
1 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 repository9 other files it gives its agents.
- ai-brainSkill
- assumption-checkSkill
- cover-letter-loopSkill
- design-inspoSkill
- luno-osSkill
- research-to-vaultSkill
- skill-routerSkill
- telegram-bot-factorySkill
- vault-librarianSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 23
Dedup: search the target store for an existing memory on this topic.
- Distinctive: line 28
Don't write the same fact into two stores.
- Distinctive: line 29
Don't put session-only detail into auto-memory.
- Very specific: line 30
Don't bloat MEMORY.md with content — one pointer line only.
“Common” is measured: kept by at least 6 in 10 of the 10 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 Hygiene
Christian has three memory stores that drift and overlap. This routes each fact to exactly one home.
The three stores
- Obsidian vault
Memory.md— the human-facing source of truth and activity log. Personal/business narrative, project state, decisions. ~/.claude/projects/-Users-chanjalme/memory/(auto-memory) — facts that should load into EVERY Claude session: preferences, identity, references, recurring feedback. One fact per file + a one-line pointer inMEMORY.md.~/.remember/buffer — short-term session history (now/today/recent). Ephemeral, rolls up automatically. Do not hand-curate.
Routing rules
- Cross-session preference / how-I-should-work / identity / reference URL → auto-memory file (type: user/feedback/project/reference).
- Project/business narrative, decisions, plans → vault (via vault-librarian).
- "What we did this session" → leave it to
.remember, don't duplicate into auto-memory.
Before saving (always)
- Dedup: search the target store for an existing memory on this topic. Update it instead of creating a duplicate. Delete memories that turn out wrong.
- Worth it? Skip anything derivable from the repo, code, or git history. If asked to remember something obvious, save the non-obvious why instead.
- Format: auto-memory needs frontmatter (name, description, metadata.type) + a one-line
MEMORY.mdpointer. Convert relative dates to absolute (UTC+8).
Anti-patterns
- Don't write the same fact into two stores.
- Don't put session-only detail into auto-memory.
- Don't bloat
MEMORY.mdwith content — one pointer line only.
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.