review-tests

review-tests is a command for coding agents from coleam00/Archon. It costs 0 tokens per session (778 once invoked), scanned A, original, MIT.

A read-only test review checks whether meaningful behavior introduced or changed by a code change is protected by a test that would fail if it regressed.

In plain words
What is it for?
Use it to map promised behavior and invariants to existing test assertions and identify realistic unprotected regressions.
Why use it?
It finds important behavior that could break later without any test warning, without treating test count or coverage as proof.

Command

About the project

Archon is a workflow engine for AI coding agents that turns development processes into YAML-defined sequences with phases, validation gates, and artifacts. Developers use it to run repeatable processes such as planning, implementation, testing, code review, and pull-request creation across projects. The catalogue entries provide commands, agents, skills, hooks, instructions, and settings for working with Archon.

coleam00/Archon · 23,374 stars · on GitHub · archon.diy

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 commands/coleam00/archon/review-tests
Clone the repo
git clone --depth 1 https://github.com/coleam00/Archon

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 review-tests

README.md
[![agentmods](https://agentmods.dev/badge/commands/coleam00/archon/review-tests.svg)](https://agentmods.dev/commands/coleam00/archon/review-tests)
Your own site
<a href="https://agentmods.dev/commands/coleam00/archon/review-tests"><img src="https://agentmods.dev/badge/commands/coleam00/archon/review-tests.svg" alt="Measured on agentmods" height="20"></a>
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 778 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 5.1 $0.00000 $0.00778
Opus 5 $0.00000 $0.00389
Sonnet 5 $0.00000 $0.00156
Haiku 4.5 $0.00000 $0.00078

Measured 6d ago against content hash 45020fd0863c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

review-tests 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 6d 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.

.archon/workflows/sdlc/review/commands/review-tests.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Review — Regression Protection

Find one defect: the change establishes or alters meaningful behavior, and no test would fail when that behavior regresses in a plausible way. Tests protect outcomes and invariants — count, lines, and coverage percentages are not outcomes. Read-only: never modify files, commit, or post anywhere.

Read $ARTIFACTS_DIR/review/scope.md first, and the project's architecture.md if it has one. Anchor the review on the accepted work order's stated invariants, and scale depth to what the change can destroy: irreversible or destructive paths, lifecycle ownership, persisted contracts and schemas, credentials and auth boundaries, integration boundaries, and concurrency over shared state each get an explicit attempt to refute the invariant they rest on; a prose-only change gets the minimum. In light mode, verify prior findings from this lens first, then examine only the delta.

A finding needs all four

  1. Behavior or invariant — what the change promises and why it matters.
  2. Coverage map — the existing tests (any level) that do and do not protect it; inspect assertions, not test titles.
  3. Plausible regression — a realistic future edit that violates the behavior while every current test still passes.
  4. Smallest valuable test — setup, action, observable assertion; it fails for that regression, passes for the intended implementation, and survives a behavior-preserving refactor.

Never report "missing test for line X" — name the observable failure that remains unprotected. Before reporting, falsify the gap: search for tests under other names, check whether types or schemas already make the regression impossible, and confirm the path is supported behavior.

Prefer leverage

Prioritize gaps where regression means incorrect user-visible behavior, data loss, failure semantics becoming success, or resume/concurrency/ordering breaks. Test at the lowest stable boundary that proves the behavior — and only at the unit level when it can prove it without mocking the behavior under review away. Check the existing doubles and fixtures for exactly that: a mock that omits the changed behavior makes every test through it blind to the change, which no amount of assertion-reading reveals.

Read the full file on GitHub · 37 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. 6d ago First seen · 37 lines · 0 tokens per session scan A 45020fd0863c

Subscribe to this mod's changes

review-tests is a command published in the GitHub repository coleam00/Archon (23,374 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 778 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 2026-08-30.