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
# Working in this repository
Rules for an agent working in this repository. [CONTRIBUTING.md](CONTRIBUTING.md) covers setup, the quality checks and the change workflow in detail.
- Branch off `main` and open a pull request against `main`. Never commit or push on `main`: the maintainer merges.
- Commit messages use conventional-commit prefixes, scoped to a subsystem where one fits (`fix(health-check): ...`, `docs(readme): ...`; `chore: ...` needs no scope); match `git log --oneline -20`.
- Write no em dashes (U+2014) in anything you add, commit messages included: use a colon, a comma, parentheses or a new sentence.
- `npm run quality` must pass before you push, and the pre-push hook runs it. Fix the cause; never bypass a hook.
- A change a user or a pipeline can notice takes a change fragment in `changes/`. A change to the shipped code that nobody can notice takes a `Changelog: none (<reason>)` line in a commit message instead. Run `npm run changes:pr` after committing, before you push.
- Changes to the memory store (`memory/`, `MEMORY.md`, `.iwe/`) go in their own `chore(memory):` commits, never with code or docs.
…
The line at the top of this page pins the label git:20261024.48f8a5d, 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_mw2fwqmoasvtfigs
GET https://markdownregistry.com/api/v1/resolve?ref=armelhbobdad/bmad-module-ultracode-goal/CLAUDE.md
GET https://markdownregistry.com/api/v1/blob/ef18aed47abbcd089902744859b7c5a8779171f9b7d7bf905ed3b44661b825e7
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.
armelhbobdad/bmad-module-ultracode-goal · skf-skills/bmad-builder/2.2.2/bmad-builder/SKILL.md · Describes the BMad Builder v2.2.2 module (code bmb): the skills it registers under skills/ — bmad-agent-builder…
armelhbobdad/bmad-module-ultracode-goal · skf-skills/bmad-method-installer/6.12.0/bmad-method-installer/SKILL.md · Module discovery and registration internals of the bmad-method v6.12.0 installer (npx bmad-method install): where it…
armelhbobdad/bmad-module-ultracode-goal · skf-skills/cc-primitives/2.1.283/cc-primitives/SKILL.md · Claude Code v2.1.283 primitives that UltraCode Goal composes, from the official docs: /goal, Auto Mode and permission…
armelhbobdad/bmad-module-ultracode-goal · skf-skills/cc-primitives/2.1.306/cc-primitives/SKILL.md · Claude Code v2.1.306 primitives that UltraCode Goal composes, from the official docs: /goal, Auto Mode, permission…
