Writing a project's rules, the instructions that apply only when they are relevant, under `.agents/rules/`. Covers deciding whether something is a rule, `AGENTS.md` or a Skill, choosing the trigger, writing patterns in the supported glob dialect, wording a rule as a convention, deciding when a rule belongs in a shared plugin and moving it there, and proving it with `uze agent rules check`. Use when asked to create, add or write a rule, when an instruction "only applies to src/…" or to one kind…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# UZE: a project's rules, written once
A rule is a Markdown file directly under `.agents/rules/` in the checkout,
versioned with the project. Its frontmatter says when it applies:
```markdown
---
trigger: glob
globs: "**/src/ui/**/*.rs"
---
Colours come from the theme: name a `Token`, never an RGB value.
```
Antigravity reads `.agents/rules/` itself. Claude Code, Codex and OpenCode
receive the same files through the rules engine `uze setup` installs. Every
harness reads the one directory and the one format, so a rule is written
once.
A subfolder of `.agents/rules/` is read only once `.agents/rules.json`
registers it, the way Antigravity reads it and so UZE and the engine too:
```json
{"entries": [{"path": ".agents/rules/team"}]}
```
`path` is relative to the checkout root, not to the manifest. A folder
entry reads the `*.md` directly in it, a file entry that one file;
`include_only` and `exclude` list paths relative to the entry. A manifest
that does not parse registers nothing, and `inherits` reaches Antigravity
alone. Keep the project's own rules flat unless a folder genuinely helps,
and never add or edit an entry naming a plugin's folder: those are UZE's.
…
The line at the top of this page pins the label git:20261019.4ff171d, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_g6kzdpsd67nqtyxr
GET https://markdownregistry.com/api/v1/resolve?ref=uze-sh/uze/rules
GET https://markdownregistry.com/api/v1/blob/c1da36d7c3fe113d141f9f902026746e72bc1e59a7b1d671c0655b74c6f67bc1
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
uze-sh/uze · .agents/skills/conformance-debug/SKILL.md · Fast, targeted debugging of the Harness Conformance Lab (conformance/) — use whenever a conformance check fails…
uze-sh/uze · .agents/skills/design-system/SKILL.md · The design system for everything UZE draws or prints - the workspace TUI (src/ui/), the CLI's output and help…
uze-sh/uze · .agents/skills/harness-watch/SKILL.md · Surveying what the supported harnesses (Claude Code, Codex, OpenCode, Antigravity CLI) shipped since UZE last looked…
uze-sh/uze · .agents/skills/journey-author/SKILL.md · Writing, changing or debugging a product journey (journeys/) — use whenever you are adding a scenario for a user-facing…
uze-sh/uze · .agents/skills/openspec-apply-change/SKILL.md · Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or…
uze-sh/uze · .agents/skills/openspec-archive-change/SKILL.md · Archive a completed OpenSpec change in the experimental workflow. Use when the user wants to finalize and archive a…
uze-sh/uze · .agents/skills/openspec-explore/SKILL.md · Enter OpenSpec explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying…
uze-sh/uze · .agents/skills/openspec-propose/SKILL.md · Propose a new OpenSpec change with all artifacts generated in one step. Use when the user wants to quickly describe…
uze-sh/uze · .agents/skills/openspec-sync-specs/SKILL.md · Sync delta specs from an OpenSpec change to main specs. Use when the user wants to update main specs with changes from…
uze-sh/uze · .agents/skills/openspec-update-change/SKILL.md · Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use…
code-yeongyu/oh-my-openagent · packages/omo-codex/plugin/components/rules/skills/rules/SKILL.md · Use when the user asks about Codex Rules behavior, injected project rules, supported rule file locations, matching, or…
mikeprasad/aria-knowledge · plugin-claude-cowork/skills/rules/SKILL.md · Quick lookup into working rules. Use when user says "/aria-cowork:rules", "/aria-cowork:rules 22", "/aria-cowork:rules…
mikeprasad/aria-knowledge · plugin-openai-codex/skills/rules/SKILL.md · Load and apply ARIA working rules, user rules, examples, and the change decision framework. Trigger on /rules, show…
mikeprasad/aria-knowledge · plugin-antigravity/skills/rules/SKILL.md · Quick lookup into working rules. Use when user says '/rules', '/rules 22', '/rules dependencies', 'look up rule…