codument: Skill for Claude Code

.agents/skills/review-work/SKILL.md

review-work is a skill for Claude Code, Codex from jakubsuplicki/codument. It costs 24 tokens per session (2,093 once invoked), scanned A, original, Apache-2.0.

A review procedure for checking the current code changes against the approved plan, tests, documentation, registry, and architecture boundaries. For larger changes, it requires an independent reviewer to challenge the work before it is committed.

In plain words
What is it for?
Use it after implementing a planned step and before committing. It prepares the relevant rules, tests, diff, and project facts for review, then applies either an adversarial review or a smaller deterministic check.
Why use it?
It catches changes that do not meet the documented requirements or cross ownership and architecture boundaries. The independent pass reduces the risk of relying only on the author's own review.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents); mentions Codex.

This is jakubsuplicki/codument's own configuration. It tells Claude Code and Codex how to work on codument itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything codument configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jakubsuplicki/codument. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jakubsuplicki/codument/main/.agents/skills/review-work/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jakubsuplicki/codument

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 review-work

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jakubsuplicki/codument/review-work"><img src="https://agentmods.dev/badge/skills/jakubsuplicki/codument/review-work.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,093 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00024 $0.02093
Opus 5 $0.00012 $0.01046
Sonnet 5 $0.00005 $0.00419
Haiku 4.5 $0.00002 $0.00209

Measured 9d ago against content hash ad7ad0eb0c49, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

review-work 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 9d 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/skills/review-work/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Work

Use this after a planned step has been implemented and before committing.

Adversarial pass (the independent reviewer)

AI must never be trusted to grade its own work. For a non-trivial diff, run an INDEPENDENT adversarial review before committing — a reviewer that assumes the change is wrong until a reproduction proves otherwise. codument review --require-review is the arbiter of "non-trivial": it requires the pass for more than one real change, any deletion, a config/data change, a risk touch, an ownership ambiguity, a module-level change, or anything beyond a single resolved symbol. A genuinely trivial diff skips this pass (the gate says so) and gets only the deterministic self-review below.

  1. Assemble the oracle. codument review --bundle > .codument/review-bundle.json — the touched features' documented invariants, the tests that pin them, the diff, and the ownership/blast facts. It adds no new source of truth; it hands the adversary a contract to attack instead of an open-ended hunt. When a review of this same base is already recorded, the bundle scopes itself to what has moved since (scope: "delta") and carries the rest as alreadyReviewed + priorFindings; --full forces the whole change set for a deliberate fresh attack. The bundle carries a stamp — a digest of exactly what it handed over — and step 3 records it, so the attestation says what it was grounded in rather than only what it concluded.
  2. Run the adversary against the bundle — independence by context, degraded gracefully.
    • Subagent host (Claude): spawn a FRESH adversarial-reviewer subagent fed ONLY the bundle — never your transcript or your reasoning, so it cannot re-anchor to the author's mental model. It reads git diff <base>, attacks the invariants, writes a failing test for each real bug, and emits a findings JSON.
    • No-subagent host (Codex): run the same adversarial pass yourself against the bundle, with deliberately fresh eyes — apply the adversarial-reviewer mandate as if you had not written the code. Independence is weaker, but the deterministic confirm and the fingerprint-bound artifact are identical, so it is not theater.
  3. Record the verdict. codument review --record <findings.json> writes the fingerprint-bound artifact. Copy the bundle's stamp into the findings JSON as bundleStamp, so the record says which oracle it answered. Any later edit to a reviewed source — or to a finding's named test — auto-invalidates it, so you cannot review once and keep editing. A review that records no stamp is still accepted: it is reported on the verdict line, never refused, because refusing it would dead-end the first review of any diff and would be walked past by anyone willing to omit the field.
  4. Enforce. codument review --require-review. It RE-RUNS each finding's named test and blocks only on one that is genuinely red — never on a claimed status. Fix every confirmed (red-test) finding before committing; advisory findings are surfaced for your decision, never auto-blocking.

Read the full file on GitHub · 91 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. 9d ago First seen · 91 lines · 24 tokens per session scan A ad7ad0eb0c49

Subscribe to this mod's changes

review-work is a skill published in the GitHub repository jakubsuplicki/codument (47 stars, last pushed 18d ago), licensed Apache-2.0. It adds 24 tokens to every session and 2,093 once invoked, about $0.0001 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.