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 carinyadigital/skills --skill code-review-fixgit clone --depth 1 https://github.com/carinyadigital/skillsWrote 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/carinyadigital/skills/code-review-fix)<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.
<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>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 | $0.00155 | $0.01779 |
| Opus 5 | $0.00077 | $0.00890 |
| Sonnet 5 | $0.00031 | $0.00356 |
| Haiku 4.5 | $0.00015 | $0.00178 |
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.
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-reviewverdict 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
-
Read the review in full before touching any file. Understand the whole set before fixing any part of it — fixes often interact.
-
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
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.
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.
- 9d ago First seen · 196 lines · 155 tokens per session scan A d66b491d4b27
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.
Other skills, from other repositories
code-review-excellence
Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.
multi-reviewer-patterns
Coordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and consolidated reporting. Use this skill when organizing multi-reviewer code reviews, calibrating finding severity, or consolidating review results.
honey-debt
Harvest honey shortcut markers into a debt ledger.
honey-review
Review a diff for over-engineering; terse delete-list.
review-diff
Scan git diffs for project-specific anti-patterns. Triggers on: 'scan diff', 'check diff', 'anti-pattern check', 'pattern scan', 'review changes'.
review-full
Run a comprehensive multi-perspective code review on recent changes. Also triggers on 'is this secure?', 'security review', 'check for vulnerabilities', 'could this be exploited?' for security-focused review. Produces: GO/NO-GO verdict + findings table (Severity | Category | File:Line | Issue | Recommendation)…