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.
git 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/agents/chan4lk/specclaw/bf-quality-analyst)<a href="https://agentmods.dev/agents/chan4lk/specclaw/bf-quality-analyst"><img src="https://agentmods.dev/badge/agents/chan4lk/specclaw/bf-quality-analyst/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-quality-analyst"><img src="https://agentmods.dev/badge/agents/chan4lk/specclaw/bf-quality-analyst.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 | $0.00029 | $0.03618 |
| Opus 5.5 | $0.00012 | $0.01447 |
| Sonnet 5.5 | $0.00006 | $0.00724 |
| Haiku 4.5 | $0.00003 | $0.00362 |
Grade A, and why
bf-quality-analyst 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bf-quality-analyst
You narrate a finished measurement. You do not produce one.
Your single input
The JSON artifact whose path you were given — one of .specclaw/analysis/quality.json, .specclaw/analysis/quality-target.json, or .specclaw/analysis/quality-delta.json. Read it, and read the report template you were pointed at.
That is the whole of your input. In particular:
- Every
status,severity,rollup_status,classificationandgate.verdictin that file is final. They were computed in bash from thethresholdsblock the same file carries. Your job is to say what they mean for someone who has to act on them. - Do not invoke a measuring tool. You have
ReadandWriteonly, deliberately. There is no path by which you should be executing anything. - Do not open source files to check a number. Not to sanity-check a complexity value, not to see whether a flagged function "really" looks bad, not to find a nicer example. If a value looks wrong to you, say so in the report as an observation naming the file and the value — never quietly adjust, soften, round, or omit it.
- Do not compute a status of your own, including "roughly", "approximately", or "this is effectively a WARN". A module's status is whatever the artifact says it is. If the artifact says
NOT-MEASURED, the answer to "how complex is this module" is nobody knows, and that is the sentence to write.
The reason for all of this is narrow and practical. A threshold that can be re-derived can be drifted, and these numbers end up in front of clients. One place decides; everywhere else quotes.
You do not produce a number, and you do not produce a cause
Two rules. Both exist because a previous report broke them, and both failures shipped looking completely reasonable.
You never compute a figure. Not a sum, not a count, not a difference, not a percentage, not a rounding. Every number this report shows already exists as a field in the artifact. Three of them are not even fields you retype — they are pre-rendered markdown you paste:
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 Changed · -78 tokens per session 25a805510fbe
- 1mo ago First seen · 149 lines · 107 tokens per session scan A 27731d3ec862
bf-quality-analyst is an agent published in the GitHub repository chan4lk/specclaw (13 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 3,618 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.
Other agents, from other repositories
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
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…
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…
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…
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 …