astack
AGENTS.md0 starsChanged 53 days agoMITView on GitHub
Edit global instructions in instructions/. Root AGENTS.md and CLAUDE.md apply only to this repository. Before creating, importing, or modifying a skill, follow the repository-local author-skill workflow. Put reusable lessons in the applicable skill or principle, and change history in the PR. Keep adaptation records in the manifest and PR instead of separate adaptation reports. Discover skills through astack-help and installed metadata; do not maintain skill inventories in the README or other overview documents. Run python3 -m unittest discover -s tests…
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 31,774 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 repository50 other files it gives its agents.
- instructions/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- instructions/CLAUDE.mdCLAUDE.md
- author-skillSkill
- architectSkill
- arenaSkill
- astack-helpSkill
- astack-updateSkill
- brag-slimSkill
- bug-fixSkill
- claude-background-jobsSkill
- claude-routerSkill
- codex-background-jobsSkill
- create-verification-skillSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- full-sendSkill
- grillingSkill
- handoffSkill
- harden-prSkill
- hillclimbSkill
- howSkill
- implementSkill
- improve-codebase-architectureSkill
- investigationSkill
- multi-phase-planSkill
- no-commentsSkill
- open-prSkill
- orchestrateSkill
- perf-issueSkill
- principlesSkill
- prototypeSkill
- refactoringSkill
- reflectSkill
- review-prSkill
- run-jobSkill
- ship-prSkill
- show-me-your-workSkill
- t3-previewSkill
- tddSkill
- teachSkill
- technical-writingSkill
- to-specSkill
- typescript-best-practicesSkill
- unslopSkill
- wayfinderSkill
- whySkill
- wizardSkill
- worktree-cleanupSkill
- writing-for-agentsSkill
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Distinctive: line 8
Before creating, importing, or modifying a skill, follow the repository-local author-skill workflow.
- Very specific: line 11
Put reusable lessons in the applicable skill or principle, and change history in the PR.
- Very specific: line 18
Run python3 -m unittest discover -s tests -v.
≈ “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
astack repository instructions
Edit global instructions in instructions/. Root AGENTS.md and CLAUDE.md
apply only to this repository.
Skills
Before creating, importing, or modifying a skill, follow the repository-local author-skill workflow.
Put reusable lessons in the applicable skill or principle, and change history in
the PR. Keep adaptation records in the manifest and PR instead of separate
adaptation reports. Discover skills through astack-help and installed metadata;
do not maintain skill inventories in the README or other overview documents.
Verification
Run python3 -m unittest discover -s tests -v. Keep tests offline and confined
to temporary directories. Use Python 3.10+, the standard library, and Git for
scripts, with support for macOS and Linux.
The directly imported orchestration runtime retains Bun/TypeScript, and
skills/show-me-your-work/scripts/log.sh retains Bash. These upstream imports
are exceptions to the Python script convention. The background-job scripts in
skills/run-job/, skills/claude-background-jobs/, and
skills/codex-background-jobs/ also run on Python 3.9, because agents invoke
them with the system python3, which is 3.9 on stock macOS. Follow the
verification steps in CLI.md to run the
orchestration tests offline in a temporary copy. The Python suite also tests the
imported decision-log helper.
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.