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.
npx skills add dcosson/h2 --skill code-reviewgit clone --depth 1 https://github.com/dcosson/h2Wrote 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.
[](https://agentmods.dev/skills/dcosson/h2/code-review)<a href="https://agentmods.dev/skills/dcosson/h2/code-review"><img src="https://agentmods.dev/badge/skills/dcosson/h2/code-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.
<a href="https://agentmods.dev/skills/dcosson/h2/code-review"><img src="https://agentmods.dev/badge/skills/dcosson/h2/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.01565 |
| Opus 5.5 | $0.00013 | $0.00626 |
| Sonnet 5.5 | $0.00007 | $0.00313 |
| Haiku 4.5 | $0.00003 | $0.00156 |
Grade A, and why
code-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.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Review the implementation for a bead or feature. Produce a structured review doc with severity-rated findings — the same disposition-table pattern used for plan reviews, applied to code.
Inputs
$0: Bead ID (e.g.,edb-d6kq.3) or commit range (e.g.,abc123..def456)$1: Reviewer identifier (e.g.,reviewer-1, used in output filename)- Review docs directory:
docs/reviews/(created if it doesn't exist)
Critical Rules
- Do NOT review code you wrote. Fresh eyes catch more issues.
- Do NOT read other reviewers' review files for the same bead before completing your own review. Reviews must be independent.
- Review the actual code diff, not just the plan. The plan says what should be built — the review verifies what was built.
- For beads that include external/E2E/acceptance tests: the reviewer MUST execute the tests against a running system, not just review the test code. Tests that compile but were never run against the actual system are not reviewed. If the reviewer cannot run the tests (e.g., missing infrastructure), they must flag this as a blocker rather than approving.
Phase 1: Scope the Review
If given a bead ID:
- Look up the bead:
bd show $0 - Find the associated commits:
git log --all --grep="Bead: $0"and any commits on branches named after the bead - Find the plan doc referenced by the bead or its parent epic
- Identify the commit range to review
If given a commit range:
- Use the range directly
- Check commit messages for
Plan-Ref:orBead:trailers to find the associated plan doc
Gather context:
- Read the plan doc (if found) to understand intent
- Run
git diff <range>to see the full code diff - Read the changed files in full (not just the diff) to understand surrounding context
- Read any test changes to understand test coverage
Phase 2: Analyze
Evaluate the implementation for:
Correctness
- Does the code match what the plan specifies?
- Race conditions, deadlocks, or unsafe concurrent access
- Off-by-one errors, nil/zero-value handling, error swallowing
- Resource leaks (unclosed handles, goroutine leaks, missing defers)
- Crash recovery and restart safety
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.
- 1mo ago First seen · 171 lines · 33 tokens per session scan A e55bbe435c94
code-review is a skill published in the GitHub repository dcosson/h2 (163 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 1,565 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…