code-review-fix

code-review-fix is a skill for Claude Code from carinyadigital/skills. It costs 155 tokens per session (1,779 once invoked), scanned A, original, MIT.

A guide for applying code-review findings to a working code change. Code review is the process of checking code for problems before it is accepted.

In plain words
What is it for?
Use it to address blocking issues, warnings, and suggestions from a review, and to list findings that were intentionally left unchanged.
Why use it?
It helps resolve findings that require changes while keeping the code's existing behaviour and the requested scope intact.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Part of the carinyaparc-agent-skills plugin — 24 skills, 13 agents shipped together

Good fit Use it to address blocking issues, warnings, and suggestions from a review, and to list findings that were intentionally left unchanged.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/carinyadigital/skills/code-review-fix
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 carinyadigital/skills --skill code-review-fix
Clone the repo
git clone --depth 1 https://github.com/carinyadigital/skills

Made for: Claude Code.

Or install carinyaparc-agent-skills, the plugin that ships this one along with the rest of its 24 skills, 13 agents.

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-fix

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/carinyadigital/skills/code-review-fix"><img src="https://agentmods.dev/badge/skills/carinyadigital/skills/code-review-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,779 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.
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 $0.00155 $0.01779
Opus 5 $0.00077 $0.00890
Sonnet 5 $0.00031 $0.00356
Haiku 4.5 $0.00015 $0.00178

Measured 9d ago against content hash d66b491d4b27, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

code-review-fix 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.

skills/code-review-fix/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code review fix

You are a Senior Software Engineer addressing feedback from a code review. You improve the code without changing its observable behaviour and without expanding its scope.

This is the write half of the review loop. code-review produces labelled findings and changes nothing; this skill consumes those labels and changes code. It does not re-review. If the findings are wrong, say so rather than implementing them.

Input

The review output or issue list, from any of:

  • A code-review verdict in the conversation or at a given path.
  • Reviewer comments on a PR/MR.
  • A plain list of issues the user pasted.

Findings from code-review carry an action label and a Category | Severity | Confidence triple. Where labels are absent (a human reviewer's comments), infer the tier from the language: a request for change is blocking, a "consider" or "nit" is suggestion.

Scope

Address every finding at or above the threshold. Leave the rest untouched and list them under "Findings Not Addressed".

Command Addresses
code-review-fix (default) blocking + warning + suggestion
code-review-fix warning blocking + warning
code-review-fix blocking blocking only

all is an alias for the default.

Steps

  1. Read the review in full before touching any file. Understand the whole set before fixing any part of it — fixes often interact.

  2. Triage each finding by action label. Drop those below the threshold. Within scope, work blocking first. Then route by what the fix requires:

    Finding Route
    Bug, security, guideline violation Fix inline
    Best practice, behaviour-preserving Fix inline
    Best practice that alters observable behaviour Defer — new work item
    Architecture or pattern divergence Defer — needs an ADR or design decision
    Data migration or contract change beyond the finding Defer — separate change

Read the full file on GitHub · 196 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 196 lines · 155 tokens per session scan A d66b491d4b27

Subscribe to this mod's changes

code-review-fix is a skill published in the GitHub repository carinyadigital/skills (2 stars, last pushed 20d ago), licensed MIT. It adds 155 tokens to every session and 1,779 once invoked, about $0.0008 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 2026-08-31.