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 siarhei-belavus/agent-public --skill code-reviewer-agentgit clone --depth 1 https://github.com/siarhei-belavus/agent-publicWrote 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/siarhei-belavus/agent-public/code-reviewer-agent)<a href="https://agentmods.dev/skills/siarhei-belavus/agent-public/code-reviewer-agent"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/code-reviewer-agent/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/siarhei-belavus/agent-public/code-reviewer-agent"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/code-reviewer-agent.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 | $0.00074 | $0.02106 |
| Opus 5.5 | $0.00030 | $0.00842 |
| Sonnet 5.5 | $0.00015 | $0.00421 |
| Haiku 4.5 | $0.00007 | $0.00211 |
Grade A, and why
code-reviewer-agent 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer Agent
Review code in deliberate passes: correctness first, then maintainability and evolution risk. Keep the review findings-first, concrete, and economical. Prioritize bugs, regressions, unsafe assumptions, lifecycle mistakes, and missing validation over style commentary.
Core Workflow
-
Establish review scope.
- Identify the exact change set:
git diff, touched files, tests added, and any untracked files that are part of the implementation. - Read applicable
AGENTS.mdandDECISIONS.mdfiles before judging the design. - Prefer reviewing the real patch over summarizing architecture from memory.
- Identify the exact change set:
-
Run a correctness pass.
- Look for regressions in control flow, state transitions, persistence, side effects, error handling, and public contracts.
- Trace changed code through its callers and consumers. Do not stop at the edited function if the behavior depends on surrounding control flow, lifecycle, or state transitions.
- Verify that tests actually prove the claim being made; weak tests are review findings when they miss the risky path.
-
Run focused validation.
- Start with the smallest relevant tests or commands that exercise the changed behavior.
- Expand only as needed for confidence.
- Record what you actually ran so the user knows the review is grounded.
-
Run a plan-compliance pass when a plan exists.
- Compare the implemented change against the agreed plan, not just against the desired outcome.
- Flag silent deviations, missing amendments, and places where implementation changed design without human approval.
- Check whether
REVIEW_NOTEmarkers were used appropriately for non-blocking better alternatives.
-
Run a maintainability pass.
- Look for duplication, hidden coupling, scattered sources of truth, and logic that will drift if changed in two places.
- Call out design debt only when it creates a realistic future bug surface or makes the new feature harder to evolve safely.
- Prefer “this is a maintenance trap because...” over vague style criticism.
What ships with it
6 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.
- 2mo ago First seen · 212 lines · 74 tokens per session scan A 177b4c516fab
code-reviewer-agent is a skill published in the GitHub repository siarhei-belavus/agent-public (2 stars, last pushed 5mo ago), licensed MIT. It adds 74 tokens to every session and 2,106 once invoked, about $0.0003 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…