ruverdruverd/bulma/AGENTS.md

bulma

AGENTS.md1 starsChanged 49 days agoMITView on GitHub

Marketplace of Bulma agent skills. Not an application repo. - Canonical skill files live under skills/<name>/, one flat directory each, with category: graph | engine | lib in the frontmatter. - category: lib marks bundled primitives (kevin, grill-with-docs, receiving-code-review, principle-*, before-and-after, the bulma-bus protocol, the bulma-host contract). Graphs must load those, not an external marketplace. - Every skill is a sibling of every other, so all cross-skill links are ../<name>/FILE.md (../bulma-bus/PROTOCOL.md). No link may leave the skills root: the repo…

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 repository35 other files it gives its agents.
- skills/bulma-feature-delivery/adapters/claude.mdCLAUDE.md
- architectSkill
- before-and-afterSkill
- blast-radiusSkill
- bulma-busSkill
- bulma-code-reviewSkill
- bulma-developerSkill
- bulma-fdSkill
- bulma-feature-deliverySkill
- bulma-goalSkill
- bulma-hostSkill
- bulma-lstmSkill
- bulma-memorySkill
- bulma-qaSkill
- bulma-reviewerSkill
- bulmaSkill
- bulma-triageSkill
- diagnoseSkill
- figure-it-outSkill
- grill-with-docsSkill
- howSkill
- interrogateSkill
- kevinSkill
- no-commentsSkill
- principle-fix-root-causesSkill
- principle-prove-it-worksSkill
- principle-sequence-verifiable-unitsSkill
- receiving-code-reviewSkill
- tddSkill
- technical-writingSkill
- thermo-nuclear-code-quality-reviewSkill
- to-issuesSkill
- to-prdSkill
- typescript-best-practicesSkill
- unslopSkill

The file

We split this AGENTS.md into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Every skill is a sibling of every other, so all cross-skill links are ../<name>/FILE.md (../bulma-bus/PROTOCOL.md).
line 7
Very specific:
Do not write .bulma-* state in this repo.
line 13
Very specific:
After a skill edit, run bulma setup (or ./install.sh setup) if you use the symlink install.
line 15

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

AGENTS.md

skills

Marketplace of Bulma agent skills. Not an application repo.

Canonical skill files live under skills/<name>/, one flat directory each, with category: graph | engine | lib in the frontmatter.
category: lib marks bundled primitives (kevin, grill-with-docs, receiving-code-review, principle-*, before-and-after, the bulma-bus protocol, the bulma-host contract). Graphs must load those, not an external marketplace.
Every skill is a sibling of every other, so all cross-skill links are ../<name>/FILE.md (../bulma-bus/PROTOCOL.md). No link may leave the skills root: the repo root is unreachable once a skill is installed. The host contract is the bulma-host skill, not a root file, for this reason.
bulma setup links skills/<name> into shared/host skill homes. When Codex is installed, shared ~/.agents home gets managed copies so Codex does not namespace standalone skills through root plugin.json or discover duplicates. Installed layout still matches git, so no link may leave the skills root.
Invocation syntax depends on the host. Codex users invoke public Bulma skills as $bulma-<name> or select them through /skills. Never tell Codex users to run /bulma-*; Codex rejects external slash commands before skill routing. Claude Code and Grok users invoke /bulma-* or the short aliases in commands/. Skill ids stay bulma-*.
Do not write .bulma-* state in this repo. Runtime state belongs in ~/.bulma/<slug>/. User/project memory: ~/.bulma/memory.md and $BULMA_REPO/memory.md, shared by all worktrees of a repo (bulma-memory).
Graphs are host-agnostic. Harness APIs live in bulma-host. See docs/GRAPH_ENGINEER.md.
After a skill edit, run bulma setup (or ./install.sh setup) if you use the symlink install. Plugin installs pick up git updates with grok plugin update bulma. End users: bulma update.
Skill bodies stay in English. Chat follows bulma-memory (default English). Forge text (PR, review, comments) stays English. Apply Kevin to human-facing communication; keep technical evidence and machine contracts unchanged.

Download now (ZIP)

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

What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free