workflows
AGENTS.md0 starsChanged 2 months agoMITView on GitHub
Workflows contains independently installable, instruction-only engineering skills. The host owns execution tools and permissions; Continuity, when configured, owns persistent project knowledge and coordination. For prose changes, review scope, clarity and affected links. For changed skill or manifest metadata, use available host validators and check the affected inventory. For behavioral changes, evaluate relevant realistic requests rather than asserting exact wording. Reuse adequate checks and do not add a test framework for prose. Verify discovery and selected-skill installation in disposable destinations when…
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 repository7 other files it gives its agents.
- workflow-artifactSkill
- workflow-commitSkill
- workflow-docsSkill
- workflow-orchestrateSkill
- workflow-prSkill
- workflow-reviewSkill
- workflow-worktreeSkill
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 5
Keep each skill self-contained and preserve distinct task boundaries.
- Distinctive: line 8
Keep repository documentation and commit/PR content in concise English, using Conventional Commits unless explicitly directed otherwise.
- Distinctive: line 13
Verify discovery and selected-skill installation in disposable destinations when package structure or installation behavior changes.
≈ “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
Workflows contributor guidance
Workflows contains independently installable, instruction-only engineering skills. The host owns execution tools and permissions; Continuity, when configured, owns persistent project knowledge and coordination.
- Keep each skill self-contained and preserve distinct task boundaries.
- Include only guidance that changes a relevant decision or protects a concrete requirement. Reuse current context and evidence. Keep operational guidance independent of model names.
- Writing and layout defaults yield to user and project choices. Keep branch prefixes, commit types and PR types independent.
- Keep repository documentation and commit/PR content in concise English, using Conventional Commits unless explicitly directed otherwise.
- Maintain one canonical explanation. Review-only work stays read-only; browser and visual QA remain opt-in.
For prose changes, review scope, clarity and affected links. For changed skill or manifest metadata, use available host validators and check the affected inventory. For behavioral changes, evaluate relevant realistic requests rather than asserting exact wording. Reuse adequate checks and do not add a test framework for prose.
Verify discovery and selected-skill installation in disposable destinations when package structure or installation behavior changes. Before publication, validate the full skill inventory and aligned manifests. Commits, pushes, publication and changes to user installations require their corresponding authorization; do not ask again when already granted.
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.

