bmad-deep-recon

80 / 100 · Low risk

Fine to try.

By bmad-code-org/BMAD-METHOD (GitHub) · research · 55,255 stars · scanned at commit a867e16

Decision-grade research on a topic or this repository. Use when the user says "deep recon", "research this", "draft a research prompt", "process this research report", "market research", "domain research", "technical research", "competitor research", "what users say about X", "literature review", "help me choose between", "research the codebase", "research how X works here" or "why is X built this way". Not for a quick code question answered in chat.

Works with any agent that supports SKILL.md skills.

What this skill can do

Downloads and installs other software

The author does not mention this.

Found in 3 places.

skills/bmad-deep-recon/SKILL.md, line 41- Script not found: BMad is not set up here. Offer to run the `bmad` skill's setup, installing `bmad` first if you do not have it (`npx skills add bmad-code-org
skills/bmad-deep-recon/SKILL.md, line 46- Script not found, or no `output_folder`: BMad is not set up here. Offer to run the `bmad` skill's setup, installing `bmad` first if you do not have it (`npx s
skills/bmad-deep-recon/references/codebase.md, line 13**The plan gate** is the one hard stop before research: the questions with their shapes; the repository and commit, which the research reads alone, so a dirty t

Runs commands on your computer

The author does not mention this.

Found in 6 places.

skills/bmad-deep-recon/scripts/recon_kit.py, line 363def __init__(self, proc: subprocess.CompletedProcess[str]):
skills/bmad-deep-recon/scripts/recon_kit.py, line 367def git(repo: Path, *args: str) -> subprocess.CompletedProcess[str]:
skills/bmad-deep-recon/scripts/recon_kit.py, line 371return subprocess.run(

Show 3 more

skills/bmad-deep-recon/scripts/recon_kit.py, line 376def raise_unless_missing(proc: subprocess.CompletedProcess[str]) -> None:
skills/bmad-deep-recon/scripts/tests/test_recon_kit.py, line 249proc = subprocess.run(["git", *ident, *args], cwd=repo, env=env, capture_output=True, text=True, check=True)
skills/bmad-deep-recon/scripts/tests/test_recon_kit.py, line 545return subprocess.CompletedProcess(["git", *args], 128, "", stderr)

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'bmad-deep-recon' ] || [ -L ~/.agents/skills/'bmad-deep-recon' ]; then echo 'A skill folder named bmad-deep-recon already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/bmad-code-org/BMAD-METHOD' "$d" && git -C "$d" checkout --quiet 'a867e1604b365d48ea03cbd109da1066ba0c84bc' -- 'skills/bmad-deep-recon' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/bmad-deep-recon' ~/.agents/skills/'bmad-deep-recon' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'bmad-deep-recon' ~/.claude/skills/'bmad-deep-recon' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for bmad-code-org/BMAD-METHOD shows the score of its lowest-scoring skill.

SkillTrust badge for bmad-code-org/BMAD-METHOD

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/bmad-code-org/BMAD-METHOD.svg)](https://zalavijaysinh.github.io/skilltrust/repos/bmad-code-org/BMAD-METHOD/)

Score history

Date	Version	Score
2026-11-08	`a867e16`	80