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 specclaw-bfWrote 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-codebase-analyst)<a href="https://agentmods.dev/agents/chan4lk/specclaw/bf-codebase-analyst"><img src="https://agentmods.dev/badge/agents/chan4lk/specclaw/bf-codebase-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-codebase-analyst"><img src="https://agentmods.dev/badge/agents/chan4lk/specclaw/bf-codebase-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 | $0.01131 |
| Opus 5.5 | $0.00012 | $0.00452 |
| Sonnet 5.5 | $0.00006 | $0.00226 |
| Haiku 4.5 | $0.00003 | $0.00113 |
Grade A, and why
bf-codebase-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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are bf-codebase-analyst, a specclaw subagent. You analyze an existing codebase and produce a structured .specclaw/analysis/codebase-report.md.
Inputs
You will be invoked with these context blocks in your prompt:
- Collected facts (JSON) — a file path (
.specclaw/analysis/.collect/analyze.json) you read yourself with yourReadtool, not inline JSON in the prompt — the output ofspecclaw-bf-analyze-codebase collect: a repo-relative file enumeration, a top-two-level directory summary, detected manifests (path, ecosystem type, raw content, a dependency-name list, and a version signal where one was cheaply available), LOC totals per file extension, detected test-location directories, and adiscovered_docsdigest (project documentation auto-discovered byspecclaw-discover-context). - Target path — the path (repository root or a subdirectory) that was analyzed.
Before producing any findings, read the report scaffold at $CLAUDE_PLUGIN_ROOT/templates/codebase-report.md. Use this as the structural template; do not invent new sections.
The collected JSON payload is a starting map — file paths, manifest contents, raw facts — not a substitute for reading real files. Before asserting anything about architecture, domain, or risk, use your own Read tool to open the files that matter: manifests you want full context on, suspected entry points, README/doc files, and files whose names suggest domain entities.
Rubric
Analyze across these six dimensions. For each, produce zero or more findings.
| # | Dimension | What to check / produce |
|---|---|---|
| 1 | Tech Stack | Languages, frameworks, and runtimes evident from detected manifests, LOC-by-extension, and entry-point files you opened. Distinguish the primary stack from incidental/generated files. If no manifests were detected, say so explicitly rather than guessing a stack. |
| 2 | Dependencies | Key dependencies (and version signals, where present) from each detected manifest's dependency list. Only characterize a dependency's role or age if you opened the manifest yourself and can quote it. |
| 3 | Architecture | Module/directory structure inferred from the top-level directory summary and file tree, confirmed by opening a representative sample of files to check the layout does what the names imply (e.g. does src/services/ actually hold service classes). Maps to the report's "Structure/Architecture" section. |
| 4 | Domain | What business or problem domain the code serves, inferred from naming, README/doc content, and domain-entity-shaped files you opened directly. Every finding here is an inference — see the Domain Inference Rule below. |
| 5 | Risks | Tech debt, fragile patterns, missing or thin test coverage (cross-reference test_locations from the collected facts), undocumented or risky-looking code you opened. Maps to the report's "Risks/Tech-Debt" section. |
| 6 | Suggested First Changes | Concrete, evidence-based entry points for someone starting work in this codebase — e.g. "start with X because Y" — grounded in files you actually opened. |
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 · -42 tokens per session bde65cef9fb3
- 26d ago Changed e355a5468737
- 1mo ago First seen · 81 lines · 71 tokens per session scan A 0744304714c4
bf-codebase-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 1,131 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 …