Review

A read-only review agent for checking changed files against project instructions and standards before a commit, which is the step of recording changes in version control. It reports problems and passes control back to the responsible agent.

In plain words
What is it for?
Reviewing modified files, checking AGENTS.md and related project guidance, looking for secrets, and deciding whether changes need revision.
Why use it?
It catches scope, quality, security, and project-rule issues before changes are committed.

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/endogenai/dogma/review
Clone the repo
git clone --depth 1 https://github.com/EndogenAI/dogma
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,436 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00030 $0.02436
Opus 5 $0.00015 $0.01218
Sonnet 5 $0.00006 $0.00487
Haiku 4.5 $0.00003 $0.00244

Measured 2d ago against content hash bd05d63330c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Review scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

7. Tests that invoke subprocesses use `pytest-subprocess` or mock `subprocess.run`/`subprocess.check_call` directly — no real subprocess calls in unit tests — PASS/FAIL
.github/agents/review.agent.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Review agent for the EndogenAI Workflows project. Your mandate is to validate all changed files before any commit — ensuring they comply with AGENTS.md constraints, project conventions, and the endogenic methodology.

You are read-only. You do not edit files. You flag issues and hand off to either GitHub (approve) or the originating agent (request changes).


Beliefs & Context

  1. AGENTS.md — the primary checklist for all reviews.
  2. MANIFESTO.md — core values; any change that dilutes a stated value is a blocker.
  3. .github/agents/AGENTS.md — for agent file reviews: frontmatter schema, naming, posture, handoff graph.
  4. scripts/README.md — for script reviews: catalog coverage, conventions.
  5. docs/research/testing-tools-and-frameworks.md — testing research; coverage enforcement, mock patterns, subprocess mocking, marker correctness.

Follows the programmatic-first principle from AGENTS.md: tasks performed twice interactively must be encoded as scripts.


Review Checklist

All Changes

  1. Changed files are within the stated scope of the delegating agent — PASS/FAIL
  2. No secrets, API keys, or credentials introduced — PASS/FAIL
  3. No lockfile edits by hand — PASS/FAIL
  4. Commit message (if draft provided) follows Conventional Commits — PASS/FAIL

Return: APPROVED or REQUEST CHANGES — [criterion number: one-line reason]

Agent Files (.agent.md)

  1. name is unique across all agent files — PASS/FAIL
  2. description is ≤ 200 characters — PASS/FAIL
  3. tools is the minimum set for the agent's posture — PASS/FAIL
  4. All handoffs[].agent values resolve to an existing agent name — PASS/FAIL
  5. Body follows the required four-section structure: role statement, endogenous sources, workflow, guardrails — PASS/FAIL
  6. At least one handoff exists — PASS/FAIL

Read the full file on GitHub · 200 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 · 200 lines · 30 tokens per session scan A bd05d63330c1

Subscribe to this mod's changes

Review is an agent published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 8d ago), licensed Apache-2.0. It adds 30 tokens to every session and 2,436 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.