agent-review

agent-review is a skill for Claude Code, Codex from ethanaubuchon/dossier-tradecraft. It costs 78 tokens per session (1,077 once invoked), scanned A, original, MIT.

A code-review step for the /implement workflow that checks committed changes in a draft pull request. It sends the change and review rules to a separate reviewer and returns findings with severity, location, problem, and suggested fix.

In plain words
What is it for?
Use it after committing code to review a diff or pull request against acceptance criteria and a plan. It also supports a loop for fixing findings and reviewing the changes again, with a human deciding when to stop.
Why use it?
It helps catch incorrect logic, missed requirements, edge cases, and silent failures before a change is finished. It reviews committed work, so the review matches what is ready for the pull request.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions subagents; names the NotebookEdit tool.

Good fit Use it after committing code to review a diff or pull request against acceptance criteria and a plan. It also supports a loop for fixing findings and reviewing the changes again, with a human deciding when to stop.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ethanaubuchon/dossier-tradecraft/agent-review
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.

Any agent
npx skills add ethanaubuchon/dossier-tradecraft --skill agent-review
Clone the repo
git clone --depth 1 https://github.com/ethanaubuchon/dossier-tradecraft

Made for: Claude Code, Codex.

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 agent-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/ethanaubuchon/dossier-tradecraft/agent-review/github.svg)](https://agentmods.dev/skills/ethanaubuchon/dossier-tradecraft/agent-review)
Your own site
<a href="https://agentmods.dev/skills/ethanaubuchon/dossier-tradecraft/agent-review"><img src="https://agentmods.dev/badge/skills/ethanaubuchon/dossier-tradecraft/agent-review/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.

agentmods 80×15 button for agent-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/ethanaubuchon/dossier-tradecraft/agent-review"><img src="https://agentmods.dev/badge/skills/ethanaubuchon/dossier-tradecraft/agent-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,077 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00078 $0.01077
Opus 5.5 $0.00031 $0.00431
Sonnet 5.5 $0.00016 $0.00215
Haiku 4.5 $0.00008 $0.00108

Measured 1mo ago against content hash f6280f144b18, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-review 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.

skills/agent-review/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Review

The review step of /implement's repo path. Runs on committed work (never unstaged changes), inside the draft PR. Dispatches a review subagent — fed the diff plus review criteria — and returns structured findings for the recipe to act on.

Dependency-free by default: a fresh install gets working review with nothing beyond dossier-mcp. The richer pr-review-toolkit specialist panel is an opt-in override of this skill (see Project overrides), not a built-in — so /implement never requires the toolkit.

Input

  • diff — the committed change to review, as a ref range (default origin/main...HEAD) or a PR number.
  • criteria (optional) — focus areas; defaults below.
  • context (optional) — the plan-file path and the ticket / acceptance criteria, passed to the reviewer so it can check the change against intent.

Default review criteria (the floor)

  • Correctness — does the code do what it claims; do its own commands/claims hold up when checked; logic errors, edge cases, off-by-ones.
  • AC coverage — does the change actually satisfy the ticket's acceptance criteria.
  • Silent failures / error handling — swallowed errors, missing guards, fallback that hides real failures.
  • Internal consistency — self-contradiction; drift from the change's own stated contract.
  • Convention consistency — does it match sibling code/patterns in the repo.

A project override can replace or extend these. If the AC / plan context isn't provided, the reviewer flags its absence as a gap rather than silently skipping the AC-coverage and intent checks.

Process

  1. Resolve the diff — git diff <range> for a ref range, or gh pr diff <number> for a PR number — plus the list of changed files and the context (plan-file path + AC) if available.
  2. Dispatch a review subagent restricted to read-only tools (no Edit/Write/NotebookEdit — e.g. a read-only agent type), so the no-side-effects contract is structurally enforced, not just instructed. Instruct it to:
    • read the diff and the changed files in full — from the worktree: pass its absolute path in the prompt and tell the subagent to read files there (its own cwd may be the main checkout, i.e. main's versions);
    • check against the criteria and the AC / plan context;
    • be skeptical and concrete — verify claims, don't praise; where a claim is checkable (a command, a path, an invariant), check it rather than trust it;
    • return findings in the structured format below, plus a one-line verdict.
  3. Return the findings to the recipe. Do not loop or apply fixes here — the recipe owns the address→re-review loop and the human ready-to-publish gate (a primitive can't host an interactive gate).

Read the full file on GitHub · 56 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. 1mo ago Changed f6280f144b18
  2. 1mo ago First seen · 56 lines · 78 tokens per session scan A fda080e95c7e

Subscribe to this mod's changes

agent-review is a skill published in the GitHub repository ethanaubuchon/dossier-tradecraft (3 stars, last pushed 8d ago), licensed MIT. It adds 78 tokens to every session and 1,077 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

raytsystem-run-review

Independently review an raytsystem run, diff, contract, test result, or milestone checkpoint and return structured findings. Use for REVIEW, architecture/contracts/data-integrity/test critique, gate verification, or pre-promotion review; remain read-only and separate from the writer context.

romarayt/raytsystem-public-os · 62 tokens

raytsystem-security-review

Audit raytsystem changes for prompt injection, provenance bypass, path/symlink/hardlink escape, secret leakage, stale fencing, partial promotion, unsafe parsing, and unapproved side effects. Use for SECURITY REVIEW, adversarial testing, recovery review, or approval-boundary validation; remain independent and read-only.

romarayt/raytsystem-public-os · 69 tokens

retro

Mine review artifacts for recurring patterns and write project learnings.

backspace-shmackspace/claude-devkit · 14 tokens

secure-review

Deep semantic security review of code changes with data flow tracing, taint analysis, and trust boundary validation. Composable building block invoked by /audit when deployed.

backspace-shmackspace/claude-devkit · 35 tokens

collaborating-with-codex

Delegate tasks to Codex CLI for prototyping, debugging, code review, implementation handoff, cross-model second opinions, and multi-turn Codex sessions via SESSIONID.

appautomaton/agent-designer · 42 tokens

council

Five independent critic subagents in parallel on an idea, plan, design, R&R strategy, grant, or SKILL.md, then a synthesis pass that ranks findings by how much of the argument rests on them, never by vote count. A markdown work plan gets the plan roster (assumptions, pre-mortem, what to delete, alternatives per piece…

ericluo04/claude-academic-workflow · 154 tokens