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 hamzaPixl/pixl-ai --skill code-reviewgit clone --depth 1 https://github.com/hamzaPixl/pixl-aiWrote 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/hamzapixl/pixl-ai/code-review)<a href="https://agentmods.dev/skills/hamzapixl/pixl-ai/code-review"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/code-review.svg" alt="Measured on agentmods" 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 | $0.00053 | $0.03171 |
| Opus 5 | $0.00026 | $0.01586 |
| Sonnet 5 | $0.00011 | $0.00634 |
| Haiku 4.5 | $0.00005 | $0.00317 |
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 7d 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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup
Read config.json in this skill directory (if it exists):
confidence_threshold— minimum confidence to include a finding; default 70post_comments— auto-post findings as PR comments; default falsereviewers— review dimensions to run; default ["correctness", "security", "conventions"]auto_fix— automatically apply low-risk fixes; default falsereview_mode— "quick" (3 core reviewers) or "full" (8 specialists); default "quick"
If post_comments is false (default), output findings as a report only — do not call gh pr review.
Argument-level flags override config defaults (e.g. --post forces comment posting, --full forces 8 reviewers, --auto-fix enables fix-first mode).
Overview
Structured multi-agent code review for pull requests. Up to 8 parallel specialist reviewers analyze the diff through specialized lenses, findings are deduplicated, scored for confidence, and classified as AUTO-FIX (safe to apply immediately) or ASK (requires user decision).
Review modes:
- Quick (default,
--quick): 3 core reviewers (correctness, security, conventions) — for routine PRs <200 lines - Full (
--full): 8 specialist reviewers — for critical changes, large PRs, or changes touching auth/payments/data
How this differs from other review skills:
/self-review-fix-loop— reviews AND fixes working tree changes. This skill is read-only (unless--auto-fix)./cto-review— architectural critique of the full branch state. This skill focuses on the PR diff./cross-review— runs two different LLM models independently. This skill uses multiple specialist lenses on the same model.- Tech-lead agent — general quality gate. This skill runs specialized parallel reviewers with confidence scoring.
Step 1: Get the Diff
Determine the review target and extract the diff:
- PR number provided:
gh pr diff <number>to get the diff,gh pr view <number> --json title,body,baseRefName,headRefNamefor context - Branch name provided:
git diff main...<branch>(or the appropriate base branch) - Nothing provided:
git diff main...HEADfor the current branch against main
What ships with it
1 file 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.
- 7d ago First seen · 303 lines · 53 tokens per session scan A 26b60d3756bd
code-review is a skill published in the GitHub repository hamzaPixl/pixl-ai (2 stars, last pushed 4mo ago), licensed MIT. It adds 53 tokens to every session and 3,171 once invoked, about $0.0003 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…