wrench / kb
AGENTS.md7 starsChanged 47 days agoMITView on GitHub
4 other projects use a version of this.
Other versions4 projects use a version of this.
Word for word · 4
- hraness/kb★ 16100% same
- hraness/wordcell★ 16100% same
- hraness/aicharts★ 4100% same
- hraness/direct★ 2100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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.
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 31,700 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 repository29 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .agents/skills/AGENTS.mdAGENTS.md
- .agents/skills/percolate-kb/AGENTS.mdAGENTS.md
- .agents/skills/phase-final-reviewer/AGENTS.mdAGENTS.md
- .agents/skills/phase-implementer/AGENTS.mdAGENTS.md
- .agents/skills/phase-orchestrator/AGENTS.mdAGENTS.md
- .agents/skills/phase-reviewer/AGENTS.mdAGENTS.md
- .agents/skills/plan-kb/AGENTS.mdAGENTS.md
- .agents/skills/query-kb/AGENTS.mdAGENTS.md
- .agents/skills/refresh-kb/AGENTS.mdAGENTS.md
- .agents/skills/save-pdf-kb/AGENTS.mdAGENTS.md
- .agents/skills/save-url-kb/AGENTS.mdAGENTS.md
- .agents/skills/write-phase-plan/AGENTS.mdAGENTS.md
- edge/AGENTS.mdAGENTS.md
- verification/AGENTS.mdAGENTS.md
- website/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- percolate-kbSkill
- phase-final-reviewerSkill
- phase-implementerSkill
- phase-orchestratorSkill
- phase-reviewerSkill
- plan-kbSkill
- query-kbSkill
- refresh-kbSkill
- save-pdf-kbSkill
- save-url-kbSkill
- write-phase-planSkill
- ghostgetSkill
The file
We split this AGENTS.md into the rules it gives an agent
8 rules. About 0 are common, 4 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Treat this directory as one Git-backed, Obsidian-compatible Markdown vault.
- Very specific: line 13
Use vault-root wikilinks without .md, such as [[notes/context-engineering|context engineering]].
- Distinctive: line 14
Put links in explanatory prose when they carry part of the argument.
- Very specific: line 15
Keep reusable concepts as ordinary notes with type: concept.
- Distinctive: line 16
Never write reciprocal, transitive, similarity-derived, or otherwise inferred relationships into notes.
- Distinctive: line 18
Keep AGENTS.md normative and concise without removing load-bearing rules.
- Very specific: line 19
Run wordcell percolate <changed-note> --root .
- Very specific: line 21
Use wordcell context <path> --root .
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 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
Contents
index.md– the vault front door and deterministically refreshed note catalog.articles/– self-contained source captures with local attachments and capture metadata.notes/– maintained concept, entity, comparison, and synthesis notes.plans/– proposed through completed design and implementation plans.riffs/– cleaned first-person notes made from dictated or stream-of-consciousness source material.scopes/– optional pull-based context hubs mapped to selected repositoryAGENTS.mdguides.
Guidelines
- Treat this directory as one Git-backed, Obsidian-compatible Markdown vault.
- Use vault-root wikilinks without
.md, such as[[notes/context-engineering|context engineering]]. - Put links in explanatory prose when they carry part of the argument. Do not add bare reciprocal links to improve graph counts.
- Keep reusable concepts as ordinary notes with
type: concept. Store typed outbound assertions underrelationswith lower-kebab-case predicates and exact vault-root target IDs; ground each assertion in prose or evidence. - Never write reciprocal, transitive, similarity-derived, or otherwise inferred relationships into notes. Backlinks, graph traversal, and percolation candidates are disposable views.
- Preserve source authority: article bodies are captures, riffs retain the speaker's claims, and maintained notes own later synthesis.
- Keep
AGENTS.mdnormative and concise without removing load-bearing rules. A scope hub may hold rationale, history, examples, and linked decisions, but never silently overrides a guide or becomes the only home of an edit-time rule. - Run
wordcell percolate <changed-note> --root .after materially changing a note, review the cited evidence, then runwordcell refresh --root .andwordcell check --root .. - During parallel edits, each lane runs
wordcell check --root . --no-catalog; the integrating agent performs one final refresh and normal check. - Use
wordcell context <path> --root . --repo <repository>for scoped repository knowledge,wordcell listfor exact metadata or tags,wordcell graphfor the whole explicit graph,wordcell linksfor bounded relationship traversal, andwordcell searchwhen the concept may use different words.
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.

