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 mpaarating/ai-workflow-kit --skill code-reviewgit clone --depth 1 https://github.com/mpaarating/ai-workflow-kitWrote 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/mpaarating/ai-workflow-kit/code-review)<a href="https://agentmods.dev/skills/mpaarating/ai-workflow-kit/code-review"><img src="https://agentmods.dev/badge/skills/mpaarating/ai-workflow-kit/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/mpaarating/ai-workflow-kit/code-review"><img src="https://agentmods.dev/badge/skills/mpaarating/ai-workflow-kit/code-review.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 | $0.00014 | $0.01262 |
| Opus 5.5 | $0.00006 | $0.00505 |
| Sonnet 5.5 | $0.00003 | $0.00252 |
| Haiku 4.5 | $0.00001 | $0.00126 |
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 2mo 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Trigger Phrases
- "code review"
- "review this branch"
- "review my code"
- "review my changes"
Inputs
No input required. The skill reviews the current branch's changes against the base branch.
Optional inputs:
- A specific base branch: "review my code against develop"
- A file filter: "review just the test files"
- A focus area: "review with focus on naming" or "review the architecture"
Workflow
Step 1: Gather the Diff
Using local git commands:
- Identify the current branch name:
git branch --show-current - Identify the base branch (default:
main): check ifmainexists, fall back tomaster - Get the full diff:
git diff [base]...HEAD - List changed files:
git diff --name-only [base]...HEAD - Get a stat summary:
git diff --stat [base]...HEAD
If there are no changes, tell the user: "No changes found against [base]. Are you on the right branch?"
If the diff is very large (50+ files or 2000+ lines changed), warn the user and offer to review a subset (e.g., by directory or file type).
Step 2: Run Reviews in Parallel
Run two review perspectives simultaneously. Each persona is defined in a shared file — read the persona definition before starting the review.
Architect Review
Read shared/personas/architect.md for the full persona definition.
Focus areas:
- Pattern Consistency: Does the code follow established patterns in the codebase?
- Reusability: Is there existing code that should be reused?
- Simplification: Is there a simpler approach?
- Abstraction Level: Right level of abstraction for the use case?
- Responsibility: Single responsibility per function/class?
- Dependency Injection: Dependencies injectable and testable?
- Dependency Direction: Dependencies flowing correctly?
- API Design: Public interfaces intuitive and consistent?
Review the diff and identify issues. For each issue:
- Prefix with
Arch: - Tag the focus area:
[PatternConsistency],[Reusability], etc. - Rate importance: High, Medium, or Low
- Include a specific suggestion or question
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.
- 2mo ago First seen · 146 lines · 14 tokens per session scan A 1ec63f97280a
code-review is a skill published in the GitHub repository mpaarating/ai-workflow-kit (2 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 1,262 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 2026-08-31.
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"…
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…
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…
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…