Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add bmad-code-org/BMAD-METHOD --skill bmad-deep-recongit clone --depth 1 https://github.com/bmad-code-org/BMAD-METHODWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bmad-code-org/bmad-method/bmad-deep-recon)<a href="https://agentmods.dev/skills/bmad-code-org/bmad-method/bmad-deep-recon"><img src="https://agentmods.dev/badge/skills/bmad-code-org/bmad-method/bmad-deep-recon/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bmad-code-org/bmad-method/bmad-deep-recon"><img src="https://agentmods.dev/badge/skills/bmad-code-org/bmad-method/bmad-deep-recon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00109 | $0.02461 |
| Opus 5.5 | $0.00044 | $0.00984 |
| Sonnet 5.5 | $0.00022 | $0.00492 |
| Haiku 4.5 | $0.00011 | $0.00246 |
Grade A, and why
bmad-deep-recon scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
27 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/codebase.template.md 1.4 KB
- assets/research.template.md 460 B
- bmod.toml 84 B
- customize.toml 11 KB
- evals/triggers.json 2.5 KB
- references/codebase-analyzer.md 1.8 KB
- references/codebase-historian.md 1.7 KB
- references/codebase-locator.md 1.4 KB
- references/codebase-verifier.md 1.4 KB
- references/codebase.md 9.4 KB
- references/draft.md 2.0 KB
- references/finalize.md 1.8 KB
- references/html-briefing.md 2.4 KB
- references/lifecycle.md 1.1 KB
- references/process.md 1.9 KB
- references/run.md 9.3 KB
- references/selection.md 2.4 KB
- references/synthesis.md 2.7 KB
- references/verification.md 4.1 KB
- scripts/recon_kit.py 28 KB runs code
- scripts/tests/test_recon_kit.py 25 KB runs code
- types/academic-lit.md 1.5 KB
- types/competitive.md 1.5 KB
- types/domain.md 1.7 KB
- types/market.md 1.3 KB
- types/technical.md 1.6 KB
- types/user-voice.md 1.7 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago Changed f5360d925769
- 14d ago Changed · +1 lines · -52 tokens per session 88da3b07b88c
- 1mo ago Changed 099b861da96a
- 1mo ago Changed · +2 lines 389655de3973
- 1mo ago Changed · +4 lines 21f8f1c7083e
- 1mo ago Changed 8fa53f7356c7
- 2mo ago First seen · 83 lines · 161 tokens per session scan A e6de27d7c037
bmad-deep-recon is a skill published in the GitHub repository bmad-code-org/BMAD-METHOD (54,822 stars, last pushed today), with no licence file. It adds 109 tokens to every session and 2,461 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
gsd-graphify
Build, query, and inspect the project knowledge graph in .planning/graphs/.
gsd-debug
Systematic debugging with persistent state across context resets.
gsd-mempalace-capture
File a phase artifact into MemPalace; mirror decision facts into its temporal KG.
gsd-mempalace-recall
Recall decisions, patterns, and surprises from MemPalace before planning.
gsd-quick-batch
Batch several /skill:gsd-quick-shaped tasks together — planned, dispatched, and merged as one run.
gsd-map-codebase
Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents.