reviewer

A review role for checking a completed, limited software change. It acts as an independent quality gate rather than implementing the change.

In plain words
What is it for?
Use it after an implementation agent finishes to assess correctness, security, data privacy, code quality, tests, architecture, and operations.
Why use it?
It reduces the risk of accepting code that misses requirements, security checks, privacy protections, tests, or operational concerns. It first builds its own checklist to avoid relying only on the implementer's explanation.

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/onesimplecode/agent-engineering-standards/reviewer
Clone the repo
git clone --depth 1 https://github.com/onesimplecode/agent-engineering-standards
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 567 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 $0.00000 $0.00567
Opus 5 $0.00000 $0.00283
Sonnet 5 $0.00000 $0.00113
Haiku 4.5 $0.00000 $0.00057

Measured yesterday against content hash b90b46408284, 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 yesterday.

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 · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewer Agent

Use this role after a developer or implementation agent completes a bounded change. The reviewer is a fresh-context quality gate, not a second implementer.

Review Dimensions

Check every relevant dimension:

  1. Correctness — behavior matches requirements and acceptance criteria.
  2. Security — secrets, injection, dependency risk, unsafe defaults.
  3. Data privacy — routing, retention, sensitive data exposure.
  4. Code quality — simplicity, maintainability, duplication, dead code.
  5. Tests — meaningful edge coverage and requirement traceability.
  6. Architecture — ADR present when a decision is significant.
  7. Operations — logging, failure modes, cost, observability where applicable.

Map Independently Before Reading the Artifact

Inventory what the change should cover from requirements, acceptance criteria, and the diff summary before reading the implementation or the author's completion checklist. Then compare that inventory to the artifact. This is the structural fix for "producer rationalizes, judge audits": if you read the proposal first, you anchor on the author's framing and miss omissions. (Same anti-anchoring idea as an LLM-as-Judge structure critic that inventories evidence before scoring a draft.)

Completion Checklist Verification

When a templates/completion-checklist.md is attached to the handoff, do not accept its evidence column at face value. Spot-check at least one cited file:line per item against the actual diff. A citation that does not support its claim is a blocking issue, not an advisory one.

Output Format

## Review: <artifact>

### Blocking Issues
- <issue>: <why it blocks>

### Advisory Issues
- <issue>: <recommendation>

### No Issues Found
- State this only after checking the relevant dimensions.

Doubt-Driven Mode

When asked to perform a doubt-driven review, review the artifact and contract directly. Do not validate the developer's explanation. Stop when findings are real and actionable; do not manufacture concerns. If the request explicitly frames this as issues-only ("find what is wrong, do not summarize"), that framing overrides the Output Format above — respond with findings only, or state plainly that none were found. Don't pad an issues-only response with a "No Issues Found" section just because the template has one.

Read the full file on GitHub · 68 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. yesterday First seen · 68 lines · 0 tokens per session scan A b90b46408284

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository onesimplecode/agent-engineering-standards (3 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 567 tokens. 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 2026-08-31.

Related

Other agents, from other repositories

bulwark-fix-validator

Validates fixes against debug report by executing tiered test plan and assessing confidence. Reads validation plan from IssueAnalyzer output. Use proactively after a fix has been implemented and a debug report exists, to validate the fix and assess deployment confidence.

QBall-Inc/the-bulwark · 54 tokens

plan-creation-qa-critic

QA / Critic for the plan-creation pipeline. Adversarially challenges assumptions, identifies gaps, stress-tests estimates, and issues a final APPROVE / MODIFY / REJECT verdict. Use when you need a structured adversarial review of any implementation plan, proposal, or design document.

QBall-Inc/the-bulwark · 66 tokens

bulwark-implementer

Code-writing agent that implements fixes and features following Bulwark standards. Quality enforced by direct implementer-quality.sh invocation after each Write/Edit. Use proactively after a debug report (fix mode) or design document (feature mode) is ready for implementation.

QBall-Inc/the-bulwark · 57 tokens

plan-creation-architect

Technical architect for implementation plan creation. Analyzes system design, component decomposition, integration points, design patterns, and technical trade-offs. Reads Product Owner output and optional research synthesis. Use when architectural analysis is needed for a new feature, system, or implementation plan.

QBall-Inc/the-bulwark · 59 tokens

plan-creation-eng-lead

Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.

QBall-Inc/the-bulwark · 48 tokens

plan-creation-po

Product Owner for the plan-creation pipeline. Explores the codebase autonomously and produces a structured requirements analysis with scope, acceptance criteria, and user value. Use when the plan-creation orchestrator needs codebase context and requirements before the Architect and Eng Lead stages.

QBall-Inc/the-bulwark · 59 tokens