gap-skills
AGENTS.md1 starsChanged 3 months agoMITView on GitHub
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 repositoryOne other file it gives its agents.
- gapSkill
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 23
Default project inspection is read-only.
- Distinctive: line 24
Keep temporary working state separate from durable delivery evidence and environment backlog.
- Distinctive: line 28
Run the verify command after every change.
≈ “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
Project: gap-skills
Purpose
One cross-harness gap skill that routes software, analysis and local-artifact work through the smallest trustworthy delivery path.
Commands
- verify:
PYTHONDONTWRITEBYTECODE=1 python3 scripts/validate.py && PYTHONDONTWRITEBYTECODE=1 python3 -m unittest discover -s tests -v
Structure
skills/gap/SKILL.md: the only skill entry point and shared contract.skills/gap/references/: branch-specific procedures loaded on demand.skills/gap/scripts/checkpoint.py: optional file-bound evidence checker; no task runner.skills/gap/assets/: optional output templates, never project policy.tests/cases/: activation and workflow contracts.tests/fixtures/: clean repositories given to agents.tests/patches/: candidate changes applied after a fixture becomes a git repository.tests/evaluators/: hidden outcome checks kept outside agent fixtures.tests/reference-solutions/: known-green baselines proving evaluators are solvable.tests/results/: retained harness evidence and limits.
Conventions
- Preserve one user-facing skill; add a reference, asset, or deterministic script only when a real branch needs it.
- Default project inspection is read-only. Mutating another project's harness requires explicit user scope or approval.
- Keep temporary working state separate from durable delivery evidence and environment backlog.
- Claude and Codex packaging must both validate; platform-specific controls stay separate.
Verification
Run the verify command after every change. Structure checks do not prove behavioral value; update behavioral cases when routing or completion behavior changes.
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.