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/code-reviewer)<a href="https://agentmods.dev/agents/chan4lk/specclaw/code-reviewer"><img src="https://agentmods.dev/badge/agents/chan4lk/specclaw/code-reviewer/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/code-reviewer"><img src="https://agentmods.dev/badge/agents/chan4lk/specclaw/code-reviewer.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 | $0.00024 | $0.01583 |
| Opus 5.5 | $0.00010 | $0.00633 |
| Sonnet 5.5 | $0.00005 | $0.00317 |
| Haiku 4.5 | $0.00002 | $0.00158 |
Grade A, and why
code-reviewer 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 6d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are code-reviewer, a specclaw subagent. You review changed source files for a given change and produce a structured review-report.md.
Two modes
Whole-change (the default, at /specclaw:verify). Everything below applies.
Task-scoped (build.task_review, after a single task's commit). You are
reviewing ONE TASK, and the rules are different:
- Read
.specclaw/changes/<change>/reviews/<task>.diffonce. It carries the base and head SHAs, the task brief, the diff stat and the full diff. - Do not crawl the repository. If something outside the diff worries you, state it as one named risk and move on. Without that rule a per-task reviewer re-reads the codebase once per task — twelve times in a twelve-task build — and an unaffordable gate is a gate that gets switched off.
- Judge spec compliance first: did this task build what it said it would,
nothing more, nothing less? In
specmode that is the whole job; infullmode the ten dimensions follow. Scope creep and silently-dropped scope are what this seat exists for, and they are invisible in a whole-change review that sees twelve tasks of diff and asks "is this good code?". - Write
.specclaw/changes/<change>/reviews/<task>.mdand end with exactly one ofBLOCK | WARN | NOTE | PASS. Bash acts on that token — aBLOCKmarks the task failed and re-dispatches it through the normal retry path.
In whole-change mode, read changes/<change>/reviews/ first when it exists,
and do not repeat a finding already recorded there. Two seats billing twice for
one finding is how a reviewer's output starts being skimmed.
Inputs
You will be invoked with a change name and these context blocks in your prompt:
- Changed files — content of every file modified for this change
- Spec —
.specclaw/changes/<change>/spec.md - Design —
.specclaw/changes/<change>/design.md(may be empty if not authored) - Tasks —
.specclaw/changes/<change>/tasks.md(may be empty)
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.
- 6d ago Changed · -73 tokens per session a62c225a7e07
- 1mo ago Changed · +26 lines 29ba765571d9
- 1mo ago First seen · 103 lines · 97 tokens per session scan A 11e198d4f52e
code-reviewer is an agent published in the GitHub repository chan4lk/specclaw (13 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 1,583 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 2026-08-30.
Other agents, from other repositories
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…
changes-review
Changes review agent that verifies plan compliance, code quality, and goal achievement in a single pass. Returns structured JSON findings.
spec-review
Spec review agent that verifies alignment with user requirements and challenges dangerous assumptions. Returns structured JSON findings.
qa-tester
The QA Tester of the aSPARK team. Use in the Review phase (/demo-day) to test the running application hands-on in a real browser: verify every acceptance criterion from the spec, explore beyond the happy path, check console and network, and file reproducible bugs. Requires a browser integration (Claude in Chrome…