agent-memory-vault / vault-template
AGENTS.md0 starsChanged 5 months agoMITView on GitHub
All agents working in this vault treat it as the shared long-term knowledge base. Before important work, check: 1. index.md 2. _system/AGENT_MEMORY_PROTOCOL.md 3. the relevant file under 02_Agents/ 4. project files under 03_Projects/ 5. decisions under 06_Decisions/ Write only durable information: user preferences, project decisions, agent config changes, tested workflows, reusable lessons, verified source summaries. Do NOT write: secrets / API keys / passwords / cookies / tokens; unverified claims without a 待核验 marker; raw logs unless summarized; huge pasted…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 32,671 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repositoryOne other file it gives its agents.
- agent-memory-vaultSkill
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
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 3
All agents working in this vault treat it as the shared long-term knowledge base.
- Distinctive: line 5
Before important work, check:
- Distinctive: line 12
Write only durable information: user preferences, project decisions, agent config changes, tested workflows, reusable lessons, verified …
- Very specific: line 15
Do NOT write: secrets / API keys / passwords / cookies / tokens.
≈ “Common” is an estimate: at least 1 in 5 of the 41,581 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Agent Memory Operating Rules
All agents working in this vault treat it as the shared long-term knowledge base.
Before important work, check:
index.md_system/AGENT_MEMORY_PROTOCOL.md- the relevant file under
02_Agents/ - project files under
03_Projects/ - decisions under
06_Decisions/
Write only durable information: user preferences, project decisions, agent config changes, tested workflows, reusable lessons, verified source summaries.
Do NOT write: secrets / API keys / passwords / cookies / tokens; unverified claims
without a 待核验 marker; raw logs unless summarized; huge pasted content (that
belongs in a source reference via ingest.py).
Ingesting an external source (article / page / video / repo / transcript): do not
hand-write a source note — use the shared pipeline, which also propagates
bidirectional cross-references, quarantines low-quality input, and rebuilds indexes:
python3 scripts/ingest.py --agent <name> \
--title "..." --summary "<your in-context summary>" --body-file <notes> \
--url "..." --source-type <article|video|repo|transcript>See _system/WRITE_GUIDE.md for the full filing standard.
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.

