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 chan4lk/specclaw --skill bf-blueprintgit clone --depth 1 https://github.com/chan4lk/specclawWrote 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/chan4lk/specclaw/bf-blueprint)<a href="https://agentmods.dev/skills/chan4lk/specclaw/bf-blueprint"><img src="https://agentmods.dev/badge/skills/chan4lk/specclaw/bf-blueprint/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/chan4lk/specclaw/bf-blueprint"><img src="https://agentmods.dev/badge/skills/chan4lk/specclaw/bf-blueprint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00017 | $0.02496 |
| Opus 5.5 | $0.00007 | $0.00998 |
| Sonnet 5.5 | $0.00003 | $0.00499 |
| Haiku 4.5 | $0.00002 | $0.00250 |
Grade A, and why
bf-blueprint 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 24d 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
specclaw bf-blueprint
First, run specclaw-ensure-init .specclaw — idempotently creates .specclaw/ if it doesn't exist (silent if already initialized; auto-inits using the current directory's basename as the project name).
Write .specclaw/analysis/target-architecture.md: the target architecture of a brownfield rebuild, synthesised from decisions already recorded. Read-only side-command — no specclaw-validate-change call, no <change> involved, matching the analyze/architecture/domain/clarify/rebuild-plan pattern.
Why this command exists. The pipeline was asymmetric. The legacy side had architecture.md, domain-model.md and module-map.md; the target side had its architecture scattered across decisions.md, ADRs, bootstrap-plan.md and the backlog — nothing that showed the shape of the thing being built, and nothing anyone could put in front of a client.
It derives, it never decides. Every claim about the target rests on a recorded SQ/CQ/UQ decision and cites it by id. Nothing here chooses a stack, a database, a hosting model or an auth approach; where no decision exists, that part of the blueprint renders PROVISIONAL(<id>). Changing what this document says means answering a question in clarifications.md and re-running --resolve — never editing the blueprint.
It runs in the legacy repo. Like every other bf- analysis command, it writes into .specclaw/analysis/ here, and is never run in the rebuild repo. The output travels into the new repo as readability, never as something a verdict is computed from.
Step 1 — Collect
mkdir -p .specclaw/analysis/.collect
specclaw-bf-blueprint collect .specclaw > .specclaw/analysis/.collect/blueprint.json
Check the exit status before spawning. If it exits non-zero, surface its stderr message to the user verbatim and stop. There is one refusal, and it names every missing document and the command that produces each: architecture.md (/specclaw-bf:bf-architecture), module-map.md (/specclaw-bf:bf-domain), decisions.md (/specclaw-bf:bf-clarify, then --resolve). Don't retry, don't attempt a partial blueprint from partial input, never substitute your own reading of the codebase for a missing decision record, and never hand the agent a path to a half-written file.
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.
- 24d ago Changed · -228 tokens per session e9754f5e428a
- 1mo ago Changed · +1 lines 1debd38b295e
- 2mo ago First seen · 96 lines · 245 tokens per session scan A d16a270ff6ef
bf-blueprint is a skill published in the GitHub repository chan4lk/specclaw (14 stars, last pushed 3d ago), licensed MIT. It adds 17 tokens to every session and 2,496 once invoked, about $0.0001 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 2026-09-05.
bf-blueprint compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bf-blueprintchan4lk/specclaw | Skill | 14 | 3d ago | MIT | A | 17 | Claude Code |
| backloga-lottes/aSPARK | Skill | 25 | 2d ago | MIT | A | 94 | Claude Code |
| backend-developerolehsvyrydov/AI-development-team | Skill | 19 | 19d ago | MIT | A | 94 | Claude Code |
| javaolehsvyrydov/AI-development-team | Skill | 19 | 19d ago | MIT | A | 136 | Claude Code |
| secops-engineerolehsvyrydov/AI-development-team | Skill | 19 | 19d ago | MIT | A | 161 | Claude Code |
| sqlolehsvyrydov/AI-development-team | Skill | 19 | 19d ago | MIT | A | 94 | Claude Code |
| e2e-testerolehsvyrydov/AI-development-team | Skill | 19 | 19d ago | MIT | A | 72 | Claude Code |