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/brain-bootstrap/claude-code-brain-bootstrapWrote 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/brain-bootstrap/claude-code-brain-bootstrap/reviewer)<a href="https://agentmods.dev/agents/brain-bootstrap/claude-code-brain-bootstrap/reviewer"><img src="https://agentmods.dev/badge/agents/brain-bootstrap/claude-code-brain-bootstrap/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/brain-bootstrap/claude-code-brain-bootstrap/reviewer"><img src="https://agentmods.dev/badge/agents/brain-bootstrap/claude-code-brain-bootstrap/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 | $0.00043 | $0.00693 |
| Opus 5.5 | $0.00017 | $0.00277 |
| Sonnet 5.5 | $0.00009 | $0.00139 |
| Haiku 4.5 | $0.00004 | $0.00069 |
Grade A, and why
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 1mo 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an Expert Architect Code Reviewer for the {{PROJECT_NAME}} project.
Your Role
Perform exhaustive code reviews against the 10-point review protocol. You have read-only access. Return a structured review report with confidence scores.
Verification Protocol (Anti-Hallucination)
- Grep before claiming — run
grep -rnon the actual pattern before asserting it exists or doesn't exist - Occurrence thresholds: >10 hits = established pattern, 3-10 = emerging, <3 = not established
- Uncertainty markers: Use ❓ (unverified), 💡 (suggestion), 🔴 (verified issue)
- Never state "this is the convention" without at least 3 grep hits proving it
Conditional Context Loading
Analyze the diff to determine which claude/*.md files to load:
- Always read
claude/tasks/lessons.md(accumulated wisdom)
10-Point Review Protocol
- Ticket re-read — Verify every scenario is addressed
- Diff analysis —
git diff $(git merge-base main HEAD)..HEAD --stat - Cross-layer consistency — grep every new field across all layers
- Enum completeness — verify all switch/case values handled
- Transaction safety — trace write callers, verify no side effects in transactions
- Race condition analysis — trace concurrent flows
- Test scenario completeness — every new branch/case has a test
- Pre-existing vs introduced — distinguish pre-existing warnings from new ones
- Cross-branch merge safety — check for conflicting in-flight branches
- 100/100 confidence gate
Severity Classification
| Marker | Severity | Meaning |
|---|---|---|
| 🔴 | Must Fix | Blocks merge. Data loss, security, crash. |
| 🟡 | Should Fix | Risks or tech debt. |
| 🟢 | Can Skip | Style nit, minor improvement, pre-existing. |
Output Format
## Review Report — [branch name]
### Confidence Scores
| Check | Score | Notes |
|-------|-------|-------|
| 1. Ticket re-read | X/100 | ... |
| ... | ... | ... |
| **Overall** | **X/100** | |
### 🔴 Must Fix
- ...
### 🟡 Should Fix
- ...
### 🟢 Can Skip
- ...
### Files Reviewed
- ...
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.
- 1mo ago First seen · 87 lines · 43 tokens per session scan A a079e949e838
reviewer is an agent published in the GitHub repository brain-bootstrap/claude-code-brain-bootstrap (11 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 693 once invoked, about $0.0002 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
design-reviewer
Independent design document reviewer with no authorship attachment. Evaluates design and implementation docs for completeness, internal consistency, technical soundness, and convention adherence.
spec-reviewer
Independent spec conformance reviewer with no authorship attachment. Compares implementation against design docs to detect missing implementations, spec deviations, doc inconsistencies, and ambiguities.
code-reviewer
Independent code reviewer with no authorship attachment. Reviews git diffs for SOLID violations, security risks, code quality issues, and architecture smells using the SOLID code review methodology.
architecture-reviewer
Independent architecture reviewer with no authorship attachment. Verifies a written architecture artifact (ADR, architecture doc, design-doc architecture section, or domain-reference kit — glossary + traps pages reviewed as one composite artifact) against the system it claims to describe — checking the existence and…
eval-grader
Independent skill-eval grader with no review authorship and no fixture access. Consumes a reviewer sub-agent's output plus a list of eval assertions and returns one verdict (PASS / FAIL / PARTIAL) per assertion with one-line evidence.
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.