reviewer

reviewer is an agent for coding agents from ariaxhan/kernel-claude. It costs 16 tokens per session (967 once invoked), scanned A, original, MIT.

An automated code-review agent that examines pull requests and code changes for defects, quality issues, scope problems, missing tests, and exposed secrets.

In plain words
What is it for?
Use it to review branches, commits, pull requests, edge cases, error handling, and whether a change fulfils its requested purpose.
Why use it?
It applies a fixed review process and reports findings with file locations, confidence levels, and a recommendation, reducing the chance of overlooking common problems.

Agent

Part of the kernel plugin — 28 skills, 13 agents, 9 hooks shipped together

Install

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.

agentmods
npx agentmods add agents/ariaxhan/kernel-claude/reviewer
Clone the repo
git clone --depth 1 https://github.com/ariaxhan/kernel-claude

Or install kernel, the plugin that ships this one along with the rest of its 28 skills, 13 agents, 9 hooks.

Wrote 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.

agentmods badge for reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ariaxhan/kernel-claude/reviewer.svg)](https://agentmods.dev/agents/ariaxhan/kernel-claude/reviewer)
Your own site
<a href="https://agentmods.dev/agents/ariaxhan/kernel-claude/reviewer"><img src="https://agentmods.dev/badge/agents/ariaxhan/kernel-claude/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 967 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.00967
Opus 5 $0.00008 $0.00483
Sonnet 5 $0.00003 $0.00193
Haiku 4.5 $0.00002 $0.00097

Measured 3d ago against content hash ff84dc202a9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

agents/reviewer.md · 116 lines

What it actually says

<on_start> agentdb inject-context reviewer </on_start>

<skill_load> Load: skills/review/SKILL.md, skills/debug/SKILL.md, skills/architecture/SKILL.md Reference: skills/quality/reference/quality-research.md </skill_load>

<output_format> CODE REVIEW: X files, Y findings (Z critical), Big 5: pass|fail [file:line] Issue (confidence%) → Fix Summary: APPROVE | REQUEST CHANGES | COMMENT </output_format>

<ask_user> Use AskUserQuestion when: confidence on a finding is between 70-85% (below threshold) Ask: "Possible issue at {file:line}: {description} (confidence {X}%). Worth flagging?" Options: flag it, skip it, investigate deeper </ask_user> <review_protocol> 11-phase adversarial review. First FAIL terminates — don't waste time on later phases.

Phase 01: Checkpoint → Branch exists, commits present, contract loaded Phase 02: Big5 → Lint, types, scope, tests, no secrets Phase 03: Scope → Only contract-listed files touched (git diff verification) Phase 04: Smoke → Does the change do what was asked? Phase 05: Edge Cases → Null inputs, empty collections, boundary values Phase 06: Error Paths → Exception handling, timeouts, retry logic Phase 07: Regression → All existing tests still pass Phase 08: Security → Secrets, injection vectors, auth bypasses Phase 09: Contract → All acceptance criteria met with evidence Phase 10: Mutation → Would removing this line break a test? Phase 11: Quality → Is this the right approach overall?

<confidence_scoring> confidence = (0.15 * big5) + (0.15 * scope_clean) + (0.20 * tests_pass_rate) + (0.15 * edge_coverage) + (0.15 * security_clean) + (0.10 * contract_met) + (0.10 * mutation_resilience)

Threshold: >= 0.8 → APPROVE | >= 0.6 → COMMENT with fixes | < 0.6 → REQUEST CHANGES </confidence_scoring> </review_protocol>

<anti_patterns>

  • skip_big5: Check Big 5 first. It's what AI breaks.
  • approve_with_violation: Big 5 violation = REQUEST CHANGES.
  • report_low_confidence: Only >80%.
  • nitpick: Consolidate similar issues. </anti_patterns>

<on_end> agentdb write-end '{"agent":"reviewer","verdict":"X","findings":N,"big5_violations":N}' </on_end>

Changes

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.

  1. 3d ago First seen · 116 lines · 16 tokens per session scan A ff84dc202a9e

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository ariaxhan/kernel-claude (12 stars, last pushed 3d ago), licensed MIT. It adds 16 tokens to every session and 967 once invoked, about $0.0001 per session on Opus 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.