whatsappd
AGENTS.md2 starsChanged 3 months agoMITView on GitHub
Issues are tracked in GitHub Issues. Pull requests are not a triage request surface. See docs/runbooks/development/issue-tracker.md. Use the canonical needs-triage, needs-info, ready-for-agent, ready-for-human, and wontfix labels. See docs/runbooks/development/triage-labels.md. This is a single-context repository. Read CONTEXT.md and relevant decisions under docs/adr/ when present. See docs/runbooks/development/domain.md. Run pnpm state. It derives the frontier, the blocked nodes, and the open pull requests from the ## Blocked by edges GitHub already holds. No document records which node is next; the one that used to…
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 repository41 other files it gives its agents.
- ask-mattSkill
- batch-grill-meSkill
- claude-handoffSkill
- codebase-designSkill
- code-reviewSkill
- design-an-interfaceSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- edit-articleSkill
- git-guardrails-claude-codeSkill
- grillingSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- implementSkill
- improve-codebase-architectureSkill
- loop-meSkill
- migrate-to-shoehornSkill
- obsidian-vaultSkill
- prototypeSkill
- qaSkill
- request-refactor-planSkill
- researchSkill
- resolving-merge-conflictsSkill
- scaffold-exercisesSkill
- setup-matt-pocock-skillsSkill
- setup-pre-commitSkill
- setup-ts-deep-modulesSkill
- tddSkill
- teachSkill
- to-questionnaireSkill
- to-specSkill
- to-ticketsSkill
- triageSkill
- ubiquitous-languageSkill
- wayfinderSkill
- wizardSkill
- writing-beatsSkill
- writing-fragmentsSkill
- writing-great-skillsSkill
- writing-shapeSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Use the canonical needs-triage, needs-info, ready-for-agent, ready-for-human, and wontfix labels.
- Very specific: line 20
Run pnpm state. It derives the frontier, the blocked nodes, and the open pull requests from the ## Blocked by edges GitHub already holds.
≈ “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 skills
Issue tracker
Issues are tracked in GitHub Issues. Pull requests are not a triage request
surface. See docs/runbooks/development/issue-tracker.md.
Triage labels
Use the canonical needs-triage, needs-info, ready-for-agent,
ready-for-human, and wontfix labels. See docs/runbooks/development/triage-labels.md.
Domain docs
This is a single-context repository. Read CONTEXT.md and relevant decisions
under docs/adr/ when present. See docs/runbooks/development/domain.md.
Execution state
Run pnpm state. It derives the frontier, the blocked nodes, and the open pull
requests from the ## Blocked by edges GitHub already holds. No document
records which node is next; the one that used to disagreed with the graph
within a day. Standing decisions that do not change when an issue closes live
in docs/standing-decisions.md.
Operational runbooks
Production procedures live in docs/runbooks/: session faults, a stuck account
lease, libSQL recovery, credential rotation, and releasing. Read the fault
disposition table in docs/runbooks/README.md before acting on any incident —
acting against the disposition is how a 30-second reconnect becomes a QR scan.
Real WhatsApp accounts are linked on this machine
Two of them, resumable with no human, holding real conversations with real
people. Before writing anything that sends, reads their databases, or logs
anything derived from them, read
docs/runbooks/development/real-account-testing.md.
Sends are restricted to an allowlist; a message to the wrong chat id reaches a
stranger from the owner's own number and cannot be recalled.
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.

