agents-md-entry

Solid

Evaluate an open source project's AGENTS.md and produce a corpus entry for the /agents-md directory. Use when adding a project to the directory, refreshing an existing entry, or running a batch of candidate repositories.

AI & Automation 55 stars 2 forks Updated 5 days ago MIT

Install

View on GitHub

Quality Score: 83/100

Stars 20%
58
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Adding a project to the instruction library An entry consists of `content/projects/<slug>.json`, its avatar in `public/logos/<slug>.png`, and generated pinned documents under `public/files/<slug>/`. The directory, project pages, and technique filters derive from the corpus; adding a project does not require a new page implementation. This is written to be run independently, one project per run, so the work can be fanned out. Do not read the other entries before writing yours — the analysis should come from the file in front of you, not from matching the house voice of entries someone else wrote. ## Instruction sources Accept either `AGENTS.md` or `CLAUDE.md`. Inspect Git tree modes to distinguish a real symlink from an ordinary file containing an import or prose reference. Resolve symlinks within the same repository commit and analyze the actual target. Set `instructionFile` to the repository-relative path of the analyzed source (for example `CLAUDE.md` or `.agents/AGENTS.md`); omitted means root `AGENTS.md`. Check `.agents/AGENTS.md`, `.agents/CLAUDE.md`, and `.claude/CLAUDE.md` as well as root files, and inspect the tree for other nested instructions before concluding that a project has none. A folder location alone does not establish precedence. Store `references` as repository-relative paths, resolving links against the instruction file’s own directory. Use that filename in every fetch, last-change lookup, measurement, and quote check below. When both files contain...

Details

Author
modem-dev
Repository
modem-dev/ossrules
Created
1 weeks ago
Last Updated
5 days ago
Language
Python
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category