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:
Quick answer
BMad project context: set up, adopt, refresh or audit repo agent instructions (short pointer) is a free Muse skill that produces a verified AGENTS.md block per repo via conversational interview, ledger-tracked instruction assessment and user-approved writes, so agent instructions for a repo are set up, refreshed or audited with approval. Short pointer listing.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit bda3c59Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. 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://raw.githubusercontent.com/bmad-code-org/BMAD-METHOD/bda3c5929f672019b90f39a3ea27259d35d00974/skills/bmad-project-context/SKILL.md Pinned version: install the code at commit bda3c5929f672019b90f39a3ea27259d35d00974 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 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.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- bda3c59 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 18, 2026 · Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 12, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill 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 skill before installing it.