remember
Skill0 starsChanged 4 months agoMITView on GitHub
This skill should be used when the user says "remember this", "save this to memory", "add a memory", "note this for next time", "update MEMORY.md", "write this down so you don't forget", or when a durable non-obvious fact, decision, or working-style correction emerges that should persist across sessions. Trigger whenever something worth keeping is established that the repo itself does not already record. Enforces the memory file format and keeps the hot index healthy.
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 repositoryOne other file it gives its agents.
- memory-gcSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.
0
Common
Most of the 61 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
If it only matters to this conversation, do not save it.
- Very specific: line 65
Keep the MEMORY.md line to ONE line.
- Very specific: line 69
If MEMORY.md now has more than ~8 ACTIVE NOW entries or is over ~10KB, demote the stalest finished thread to MEMORY-INDEX.md (fold any …
- Very specific: line 76
Never delete a memory. Superseded ones move to _archive/ (that is memory-gc's job).
“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: write to memory correctly
Governing doc: MEMORY-ARCHITECTURE.md in the memory dir. Read it if a rule is unclear.
This skill is the WRITE path. Maintenance is memory-gc.
Step 0: should this be a memory at all
Save it only if BOTH are true:
- a future session needs it to act correctly, and
- it is not derivable from the code, git history, or an existing
CLAUDE.md.
If it only matters to this conversation, do not save it. If the repo already records it, do not save it. If asked to "remember" something the code already says, ask what was non-obvious about it and save that instead.
Step 1: pick the type and the slug
- user who the user is, role, preferences, how they like to work.
- feedback a correction or a confirmed approach. MUST include the why.
- project ongoing work, goals, constraints not in the code/git.
- reference a pointer to an external resource.
Slug: undated for a standing rule (prefer_pytest), dated YYYY_MM_DD for an event
(auth_refactor_shipped_2026_01_15). Filename matches the slug.
Step 2: check for an existing file first
Grep the memory dir for the topic. If a file already covers it, UPDATE that file. A new dated sibling is only for a genuinely new event, not new detail about an old one. This is where duplicates come from, so check before creating.
Step 3: write the file
---
name: <slug>
description: <one line, a decision hook: when would a future session need this>
metadata:
type: user | feedback | project | reference
---
<the fact, stated plainly.>
**Why:** <for feedback/project. the reason, so it is not re-litigated later.>
**How to apply:** <the concrete action a future session should take.>
Related: [[other_slug]]The description is a hook, not a summary. "when touching auth, read this", not
"about auth". Link related memories with [[slug]].
Step 4: index it in the SAME edit (non-negotiable)
An unindexed file is an orphan: it silently stops existing for future sessions. In the same change:
- open thread that is active right now -> add a one-line entry to
MEMORY.mdACTIVE NOW. - a standing rule -> the rules section of
MEMORY.md. - everything else -> the right category in
MEMORY-INDEX.md.
Keep the MEMORY.md line to ONE line. Detail stays in the topic file.
Step 5: keep the hot index honest
If MEMORY.md now has more than ~8 ACTIVE NOW entries or is over ~10KB, demote the
stalest finished thread to MEMORY-INDEX.md (fold any hot-only detail into its topic
file first). If unsure what to demote, run memory-gc.
Hard rules
- One fact per file.
- Never delete a memory. Superseded ones move to
_archive/(that ismemory-gc's job). - Index line and file in the same edit, always.
- The hot index is a table of contents, never a content store.
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.

