BMad project context: set up, adopt, refresh or audit repo agent instructions (short pointer)
Produces a verified AGENTS.md block per repo via conversational interview, ledger-tracked instruction assessment, user-approved writes — short pointer
- What
- Produces a verified AGENTS.md block per repo via conversational interview, ledger-tracked instruction assessment, user-approved writes — short pointer
- Cost
- Free
- Needs
- a target repo to document (BMad project setup with _bmad/ folder recommended, standalone usable); no license declared in the source repo — read it yourself before reusing its content
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — a short pointer to @bmad-code-org's bmad-project-context workflow: a conversation that produces a repository's agent instructions as a small verified block inside `AGENTS.md`. The user brings governance/security/standards rules, the repository supplies the rest — verified, never guessed. Five intents: setup (greenfield), adopt (existing instruction file without a managed block), refresh (managed block exists — diff against the recorded SHA), record (capture one observed agent mistake as a pitfall), and audit (re-verify every caveat and path, shrink or prune). The core loop: assess and report against `references/best-practices.md` with a ledger entry per existing instruction (retain/rewrite/relocate/automate/delete with reason, evidence and approval flag); ask the user for outside documents; discover and verify by scanning configs/CI/source rather than asking; interview only the gaps (recall questions, batches of at most eight, never ask what a scan could answer); show the complete block plus the settled ledger before writing; splice between markers; close with what went in, what was left out and why. Rules: no writes until step 5, show the block before writing it, never commit, deletions need one of four grounds. Honest caveats: **no license declared in the repository manifest — license unknown**, so this is a short fiche linking to the source, without reusing its content; designed to run inside a BMad project (`_bmad/` folder) though usable standalone; conversational by design — the user approves every write. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: a target repo to document (BMad project setup with _bmad/ folder recommended, standalone usable); no license declared in the source repo — read it yourself before reusing its content Install "BMad project context: set up, adopt, refresh or audit repo agent instructions (short pointer)" for me. Fetch the SKILL.md from the source repository into a temporary folder, review it for anything suspicious, and report in two or three sentences what the bmad-project-context workflow covers (conversational AGENTS.md block production, ledger-tracked assessment, verify-don't-guess discovery, show-before-write, five intents: setup/adopt/refresh/record/audit) so I can run it against my own repo. Do not copy the workflow's content into my project — this is a reference lookup only. Repository: https://github.com/bmad-code-org/BMAD-METHOD/blob/main/skills/bmad-project-context/SKILL.md GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Rules: don't touch anything outside the temp folder. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.