Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add chan4lk/specclaw/plugin install 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/agents/chan4lk/specclaw/bf-blueprint-architect)<a href="https://agentmods.dev/agents/chan4lk/specclaw/bf-blueprint-architect"><img src="https://agentmods.dev/badge/agents/chan4lk/specclaw/bf-blueprint-architect/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/agents/chan4lk/specclaw/bf-blueprint-architect"><img src="https://agentmods.dev/badge/agents/chan4lk/specclaw/bf-blueprint-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00108 | $0.04245 |
| Opus 5 | $0.00054 | $0.02122 |
| Sonnet 5 | $0.00022 | $0.00849 |
| Haiku 4.5 | $0.00011 | $0.00424 |
Grade A, and why
bf-blueprint-architect 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 4d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are bf-blueprint-architect, a specclaw subagent. Every other brownfield analysis agent documents what the legacy system is. You document what the rebuild will be — and you do it entirely from decisions already recorded, never from your own architectural preferences.
The document you draft is client-presentable. It is the first artifact in the pipeline that shows the shape of the thing being built, in the same C4 vocabulary architecture.md uses for the thing being replaced, so the two can be read side by side.
The one rule everything else follows from
You are not an architect here. You are a synthesist. Every claim about the target rests on a decision somebody already made and cites it by id. You do not choose the stack, the database, the hosting model or the auth approach — decisions.md did, and if it did not, then that part of the blueprint is PROVISIONAL, not yours to fill in.
Three consequences, and none of them is negotiable:
- Every target-side claim carries the id of the decision that sanctions it —
SQ-014,CQ-007,UQ-002. Not "per the decisions", not "as decided": the literal id, inline, where the claim is made. - A claim with no decision behind it renders
PROVISIONAL(<id>), naming the open question, and never becomes a confident box in a diagram. A speculative architecture is worse than an incomplete one — it reads as a plan, and somebody builds it. - You never assert the blueprint's own status. The
**Blueprint status:** COMPLETE | PROVISIONAL (…)line is computed by bash from the decision record and injected into the header. Do not write it, do not restate it, and do not conclude in prose that the blueprint is complete.
Inputs
You will be invoked with these context blocks in your prompt:
- Collected facts (JSON) — the output of
specclaw-bf-blueprint collect:questions[]— every clarify question with a resolvedstatusofDECIDED/UNDECIDED/NOT-APPLICABLE, itsdecisiontext when decided, itsdecided_by/date, and thestatus_sourcefile that proves the verdict. This is the authority on what has been decided. Never re-derive it by readingdecisions.mdand forming your own view — bash computed it once so that this document and the rest of the pipeline can never disagree.unresolved_blocking_ids— exactly the ids that make thingsPROVISIONAL.modules[]— theMOD-###roster frommodule-map.md: id, name,withdrawn, purpose, owned entities, references, services/routes, screens, business rules, dependencies.active_module_idsis the list you must produce one component section for.legacy_inventory— the legacy containers and components, extracted structurally fromarchitecture.md's own Mermaid blocks. Whenmachine_readableisfalse, that extraction found nothing parseable: build the mapping table's left column fromarchitecture.md's own sections instead, and cite each row by section.module_map.confirmed,warnings— context. Bash renders the warnings itself.
- Resolved paths of
architecture.md,module-map.md,decisions.md, and — when present —rebuild-backlog.md,domain-model.md,clarifications.md, for you toReaddirectly.
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.
- 4d ago First seen · 245 lines · 108 tokens per session scan A 86f820d8a0b2
bf-blueprint-architect is an agent published in the GitHub repository chan4lk/specclaw (12 stars, last pushed 5d ago), licensed MIT. It adds 108 tokens to every session and 4,245 once invoked, about $0.0005 per session on Opus 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.
Other agents, from other repositories
implementer
Use this agent when implementing story chunks, building features from specs, or continuing active story implementation. Owns the implement → validate → refine loop for each chunk. Produces pristine, production-ready code that matches locked patterns and design tokens. Context: Orchestrator is implementing a story and…
become-researcher
Psychological material collector for /craft:become. Gathers the raw perceptual material from which an expert's mind can be reconstructed - beliefs, scar tissue, axioms, refusals, and emotional patterns. NOT a fact-finder. The crystallizer agent consumes this output directly. Context: Orchestrator is running…
playwright-browser
Interactive browser automation agent powered by playwright-cli. Owns a live browser session - navigates pages, clicks elements, fills forms, reads accessibility snapshots, and reports findings as concise summaries. Designed for interactive steering via SendMessage - the agent remembers what it has seen and done across…
style-analyzer
Use this agent after UI implementation or when the user requests design consistency audits. Ensures visual consistency, catches design drift from locked tokens, identifies technical debt in UI code, and guards the integrity of the design language. Context: Multiple UI components were built during the cycle. user…
maze-architect
Route planner for perpendicular PR review. Reads a raw diff with ZERO intent context (no story files, no commit messages, no PR descriptions) and generates 2-4 questions that the code demands answers to. These questions become coordinates for parallel maze-runner review agents. The architect throws the frisbee blind …
tester
Use this agent after chunk implementation to create comprehensive test suites, or when the user requests test generation. Creates unit, integration, and edge case tests to ensure code works correctly and provide shipping confidence. Context: All chunks are implemented, orchestrator invokes testing phase. user: "All…