code-review-incorporate

code-review-incorporate is a skill for Claude Code from dcosson/h2. It costs 42 tokens per session (1,758 once invoked), scanned A, original, MIT.

A workflow for applying findings from a code review document to the implementation. It records whether each finding was fixed, rejected with a reason, or deferred.

In plain words
What is it for?
Use it to read review findings, change the relevant code, commit those changes with links to the review, update the review's tracking table, and request another review when needed.
Why use it?
It keeps review decisions and code changes connected, so feedback is not lost or handled inconsistently.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

Good fit Use it to read review findings, change the relevant code, commit those changes with links to the review, update the review's tracking table, and request another review when needed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dcosson/h2/code-review-incorporate
View source ↗ dcosson/h2
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 dcosson/h2 --skill code-review-incorporate
Clone the repo
git clone --depth 1 https://github.com/dcosson/h2

Made for: Claude Code.

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 code-review-incorporate

README.md
[![agentmods](https://agentmods.dev/badge/skills/dcosson/h2/code-review-incorporate.svg)](https://agentmods.dev/skills/dcosson/h2/code-review-incorporate)
Your own site
<a href="https://agentmods.dev/skills/dcosson/h2/code-review-incorporate"><img src="https://agentmods.dev/badge/skills/dcosson/h2/code-review-incorporate.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,758 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 $0.00042 $0.01758
Opus 5 $0.00021 $0.00879
Sonnet 5 $0.00008 $0.00352
Haiku 4.5 $0.00004 $0.00176

Measured 8d ago against content hash e85f7ff4f648, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

code-review-incorporate 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 8d 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.

internal/config/templates/styles/opinionated/skills/code-review-incorporate/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Incorporate

Incorporate findings from a code review doc into the implementation. Make the code changes, commit with structured trailers linking back to the review, and update the review doc's disposition table.

Inputs

  • $0: Path to the review doc (e.g., docs/reviews/edb-d6kq.3-r1-review-reviewer-1.md)

Phase 1: Read & Understand

  1. Read the review doc at $0
  2. Extract: bead ID, commit range reviewed, plan doc path, reviewer name, findings list
  3. Read the plan doc (if referenced) to understand original intent
  4. Read the code files referenced in each finding
  5. Check for existing disposition tables in the review doc (from prior incorporate rounds on the same review)

Phase 2: Evaluate Each Finding

For every finding in the review doc:

  1. Read the referenced code and understand the issue
  2. Decide disposition:
    • Incorporate: The finding is valid — plan the code fix
    • Not Incorporate: The finding is invalid or the current code is intentional — prepare rationale
    • Deferred: Valid but out of scope — create a follow-up bead

Disposition Criteria

Valid reasons for "Not Incorporate":

  • The current code is intentional and the reviewer misunderstands the design
  • The change would introduce import cycles or architectural violations
  • The finding conflicts with a decision documented in the plan doc
  • The reviewer's suggested fix has correctness issues of its own

Invalid reasons for "Not Incorporate":

  • "Too much work" (effort is not a factor)
  • "Works fine as-is" (if there's a real quality issue, fix it)

Phase 3: Discussion with Reviewer

Do not apply changes yet. Reach consensus with the reviewer first.

Step 1: Send Proposed Dispositions

Send a single h2 send message to the reviewer with proposed dispositions:

Proposed dispositions for {review-doc-path}:

1. P0 - {title}: Incorporate — {brief description of planned fix}
2. P1 - {title}: Not Incorporate — {rationale}
3. P2 - {title}: Incorporate — {brief description}
...

Please confirm, or push back on any you disagree with.

Read the full file on GitHub · 182 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. 8d ago First seen · 182 lines · 42 tokens per session scan A e85f7ff4f648

Subscribe to this mod's changes

code-review-incorporate is a skill published in the GitHub repository dcosson/h2 (159 stars, last pushed 12d ago), licensed MIT. It adds 42 tokens to every session and 1,758 once invoked, about $0.0002 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.