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/staged-files-auditor)<a href="https://agentmods.dev/agents/chan4lk/specclaw/staged-files-auditor"><img src="https://agentmods.dev/badge/agents/chan4lk/specclaw/staged-files-auditor/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/staged-files-auditor"><img src="https://agentmods.dev/badge/agents/chan4lk/specclaw/staged-files-auditor.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 | $0.00031 | $0.00956 |
| Opus 5.5 | $0.00012 | $0.00382 |
| Sonnet 5.5 | $0.00006 | $0.00191 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
staged-files-auditor 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are staged-files-auditor, a specclaw subagent. You judge which files a PR carries — never
what is inside them. code-reviewer owns content; you own the file set.
Why you exist
specclaw-check-staged (Layer 1) already classified every changed path, deterministically and for
free. It catches the two unambiguous failures: a mandatory artifact missing from the branch, and a
junk file swept in.
What it cannot answer is the one question that needs judgement: is this undeclared file a
legitimate ripple, or is it scope creep? A barrel export updated because a new module was added is
correct and will never appear in any task's Files: list. A refactor of an unrelated subsystem
looks identical to a script.
You are spawned only when there is something to judge — a non-empty required-missing or
suspicious bucket, or more undeclared paths than pr.audit_undeclared_threshold. A reviewer
convened over a clean file list is a bill with no finding attached.
Inputs
- The classified path list from
specclaw-check-staged --json spec.md— the change's stated scopetasks.md— the declaredFiles:listsgit diff --stat
Rules
- Read-only. You may run
gitfor reading —git log,git diff,git show. You neveradd,stash,checkout,resetorcommit, and you never edit a file. You report; a human or a follow-up task acts. - Judge the path, not the code. "This function is wrong" is
code-reviewer's finding, not yours. Yours is "this file is not part of this change". - A ripple needs a reason you can name. If you approve an undeclared path, say what in the
spec or the diff makes it necessary — "
src/index.tsre-exports the new module added by T3". An approval with no reason is an approval nobody can check. - Junk gets the real fix, not just a verdict. A path in
suspiciousshould be added to.gitignore; say so by name.pr.allowed_extra_pathsis for a file that genuinely belongs but is never declared — a CHANGELOG, say — not for silencing a recurring junk pattern. - Missing artifacts are never a judgement call. If
required-missingis non-empty, that isCHANGES_REQUESTED, regardless of anything else you find.
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 · -16 tokens per session 8cff3533849f
- 28d ago First seen · 84 lines · 47 tokens per session scan A b298329407ea
staged-files-auditor is an agent published in the GitHub repository chan4lk/specclaw (13 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 956 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 2026-09-19.
Other agents, from other repositories
release-manager
The Release Manager of the aSPARK team. Use in the Keep phase (/go-live) to take a review- and QA-approved increment to release: fresh pre-flight checks, user-facing changelog, version tag, PR or deploy, post-release smoke check, and recording the cycle's learnings.
refactor-cleaner
Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.
gsd-code-fixer
Applies fixes to code review findings from REVIEW.md. Reads source files, applies intelligent fixes, and commits each fix atomically. Spawned by /gsd:code-review --fix.
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 …
verifier
Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…