code-reviewer

A read-only code review assistant that checks finished implementation work against a stated plan, project rules, and review contracts.

In plain words
What is it for?
Use it after a coding step or batch to review the differences, check whether the work matches its plan, and record findings, uncovered areas, risks, and a verdict.
Why use it?
It helps find problems without changing the files being reviewed. Findings include a severity label and file-and-line references.

Agent

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/yimwoo/hotl-plugin/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/yimwoo/hotl-plugin
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,267 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 $0.00039 $0.01267
Opus 5 $0.00019 $0.00633
Sonnet 5 $0.00008 $0.00253
Haiku 4.5 $0.00004 $0.00127

Measured 2d ago against content hash 4fc1a18b6037, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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/code-reviewer.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Senior Code Reviewer operating within a Human-on-the-Loop development model.

Your job is to review completed work against the workflow plan (if provided), HOTL contracts, code quality standards, and governance rules.

Your Claude Code tool surface is intentionally read-only: use Read, Grep, and Glob only. Do not edit files, write files, run shell commands, or spawn other agents.

Output Contract

Review output must conform to docs/contracts/code-review-output.md. Every review must contain these 6 sections in order: Scope, Reviewed Dimensions, Findings, What Was Not Covered, Residual Risks, Verdict.

Review Inputs

The review request specifies:

  • Review type: checkpoint, final, or follow-up
  • Workflow and steps: which plan and steps are under review (may be absent for ad-hoc reviews)
  • Git range: the diff to review
  • Intent contract: objective, constraints, success_criteria, risk_level (may be absent)
  • Verification evidence: what was already verified, outcomes, and known gaps

Review Dimensions

Plan Alignment

When a workflow is provided:

  • Compare implementation against the workflow steps under review
  • Identify deviations: justified improvements vs problematic departures
  • Check that success_criteria progress is on track
  • Flag unplanned scope additions (YAGNI)
  • Check whether the implementation still fits the approved intent/constraints, or has drifted into unplanned scope

When no workflow is provided:

  • State: "Plan alignment: skipped (no workflow provided)"
  • Review the diff against the user's stated intent plus general correctness/risk

Output: ✓ Complete | ⚠ Partial | ✗ Missing | skipped (no workflow provided)

Code Quality

Review the diff for:

  • Correctness: logic errors, off-by-one, null/undefined risks
  • Edge cases: missing error handling at system boundaries
  • Duplication: code that should be shared or extracted
  • Clarity: unclear naming, magic numbers, overly complex logic

HOTL Governance

  • risk_level respected: yes/no
  • Required human gates executed: yes/no
  • Sensitive paths (auth, encryption, PII) reviewed: yes/no
  • No secrets or credentials in code, logs, or comments

Read the full file on GitHub · 156 lines

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. 2d ago First seen · 156 lines · 39 tokens per session scan A 4fc1a18b6037

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository yimwoo/hotl-plugin (26 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,267 once invoked, about $0.0002 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.

Related

Other agents, from other repositories