Remember
Skill8 starsChanged 7 months agoApache-2.0View on GitHub
Memory hygiene workflow to classify, deduplicate, and promote durable knowledge across local memory layers.
69 other projects use a version of this.
Adopted by
Most recently taken up by
- hydra-db/hydradb-claude-codetheir own version, first seen Nov 8, 2026
- priyansh1210/shirotheir own version, first seen Nov 8, 2026
- jsmastery-pro/jsm-hqtheir own version, first seen Nov 8, 2026
- Yeachan-Heo/oh-my-claudecodetheir own version, first seen Nov 8, 2026
- ArcticFox2029/chamnantheir own version, first seen Nov 5, 2026
- Buddhilive/buddhi-clitheir own version, first seen Nov 1, 2026
Used with
Projects with it also use agent-context-isolation, agentica-infrastructure 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.
parcadeiSkillagent-context-isolation
Agent Context Isolation
Also in 3 projects that use this
parcadeiSkillagentica-infrastructure
Reference guide for Agentica multi-agent infrastructure APIs
Also in 3 projects that use this
- +10 more from parcadei
Other versions69 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 69
- github/awesome-copilot★ 41ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- langchain-ai/deepagents★ 31ksame name
- parcadei/Continuous-Claude★ 3.9ksame name
- parcadei/Continuous-Claude-v2★ 3.9ksame name
- parcadei/Continuous-Claude-v3★ 3.9ksame name
- zereight/gitlab-mcp★ 2.1ksame name
- H-mmer/pentest-agents★ 815same name
- SparkDevNetwork/Rock★ 701same name
59 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 repository38 other files it gives its agents.
- Brave SearchSkill
- BrowserSkill
- CloudflareSkill
- DNS ToolsSkill
- Docker APISkill
- Endpoint CheckSkill
- Fetch URLSkill
- GitHubSkill
- Google OAuthSkill
- GoogleSkill
- GoPlacesSkill
- LoopSkill
- Microsoft Edge TTSSkill
- 1PasswordSkill
- OpenAI WhisperSkill
- OpenStreetMapSkill
- PDF ExtractSkill
- ProxmoxSkill
- RSS / AtomSkill
- RTSP SnapshotSkill
- Session LogsSkill
- SimplifySkill
- SkillifySkill
- SpotifySkill
- SSH ExecSkill
- StuckSkill
- SummarizeSkill
- TaskFlowSkill
- Tesseract OCRSkill
- tmuxSkill
- TranslateSkill
- Update ConfigSkill
- VerifySkill
- Video FramesSkill
- WeatherSkill
- WikipediaSkill
- Wolfram AlphaSkill
- yt-dlpSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 61 edited versions we read keep these.
5
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 35
Use explicit structured args when provided.
- Very specific: line 58
If apply_changes=true, execute approved changes and re-validate consistency.
- Distinctive: line 62
Default to proposal mode; do not mutate without explicit approval.
- Distinctive: line 63
Never delete content that has unresolved ambiguity.
- Distinctive: line 64
Prefer reversible edits and clear provenance notes.
- Distinctive: line 65
Keep sensitive values out of memory docs.
“Common” is measured: kept by at least 6 in 10 of the 61 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
Remember
Review memory-like artifacts and propose what should be kept, promoted, merged, or removed. This keeps guidance accurate as the project evolves.
Use when
- Memory instructions are drifting or conflicting.
- Team wants to clean stale guidance from old sessions.
- You need to promote stable patterns into durable docs.
Do not use when
- There is no meaningful memory/context to review.
- User only needs a one-off answer (no memory maintenance).
- You are asked to auto-edit memory layers without confirmation.
Input contract
review_scope(optional):workspace_docs,session_logs,both(defaultboth).apply_changes(optional): defaultfalse(proposal mode first).priority(optional):conflicts,duplicates,promotions,all(defaultall).target_files(optional): explicit files to inspect first.
Parsing rules (priority order)
- Use explicit structured args when provided.
- Else infer from user phrasing:
- "clean memory", "dedupe instructions" ->
priority=duplicates,conflicts - "promote stable conventions" ->
priority=promotions - "just review, don't edit" ->
apply_changes=false
- "clean memory", "dedupe instructions" ->
- Defaults:
review_scope=bothapply_changes=falsepriority=all
Canonical workflow
- Collect sources
- Workspace memory docs (for example:
IDENTITY.md,SOUL.md,MEMORY.md,USER.md,AGENTS.md) and session evidence when available.
- Workspace memory docs (for example:
- Classify entries
- durable convention, temporary note, duplicate, outdated, conflicting, ambiguous.
- Generate proposals
- promotions (move to durable location), cleanup (remove/merge duplicates), conflict resolution (which version wins + rationale).
- Present grouped report
Promotions,Cleanup,Conflicts,Ambiguous,No action.
- Apply only with approval
- If
apply_changes=true, execute approved changes and re-validate consistency.
- If
Guardrails
- Default to proposal mode; do not mutate without explicit approval.
- Never delete content that has unresolved ambiguity.
- Prefer reversible edits and clear provenance notes.
- Keep sensitive values out of memory docs; redact before proposing promotion.
- State uncertainty explicitly when evidence is insufficient.
Output format
Always return:
status:proposed|applied|needs_user_inputreview_scope: effective scopepromotions: list with destination + rationalecleanup: duplicates/outdated removals or mergesconflicts: contradiction list + recommended resolutionambiguous: items requiring user decisionnext_action: required unlessstatus=applied
Example
review_scope="both" priority="all" apply_changes=false
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.

