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 Kimyongari/harness-factory --skill code-reviewgit clone --depth 1 https://github.com/Kimyongari/harness-factoryWrote 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/kimyongari/harness-factory/code-review)<a href="https://agentmods.dev/skills/kimyongari/harness-factory/code-review"><img src="https://agentmods.dev/badge/skills/kimyongari/harness-factory/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/kimyongari/harness-factory/code-review"><img src="https://agentmods.dev/badge/skills/kimyongari/harness-factory/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 | $0.00065 | $0.00514 |
| Opus 5 | $0.00032 | $0.00257 |
| Sonnet 5 | $0.00013 | $0.00103 |
| Haiku 4.5 | $0.00006 | $0.00051 |
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 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.
What it actually says
Code review
Principle: every finding ships with a reproducible failure story. Not "this looks bad" but "with this input, it breaks like this".
Procedure
- See the whole range:
git diff <base>...HEAD— never just the latest commit. - Sweep in severity order:
- Correctness: is there an input/state this diff breaks? Boundaries, None, empty lists.
- Security: does input reach shell/SQL/paths/deserialization? Do secrets land in code or logs?
- Regressions: do existing callers change behavior? Do tests cover that path?
- Simplification: can the same thing be done with less code (including existing utils)?
- Consistency: does it break this repo's conventions (naming, error handling, comment density)?
- Write each finding as
file:line — [severity] claim. Failure scenario.Severity: blocker (incident/data loss) / should (fix before merge) / nit (taste, ignorable).
Rules
- Don't fix the code yourself — a review request is not a fix request. Confirm before patching.
- If there are no findings, say so. Don't invent filler nits.
- Turn low-confidence findings into questions: "can X happen here?"
- Any blocker/should present → state the conclusion explicitly as "hold the merge".
Getting my own work reviewed
- Use a fresh context. A reviewer fed your session history inherits your assumptions —
hand over only the diff (
BASE..HEAD) and the requirements. This bundle'sreviewersubagent exists exactly for this (Claude Code:.claude/agents/reviewer). - Act on feedback by severity: blockers immediately, shoulds before proceeding; if the reviewer is wrong, don't ignore it — push back with reasoning.
Credit: the fresh-context review principle comes from obra/superpowers requesting-code-review.
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 · 37 lines · 65 tokens per session scan A 32c5ba9f331d
code-review is a skill published in the GitHub repository Kimyongari/harness-factory (5 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 514 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
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.
chimera
Use this skill for post-session code quality review of files added or modified during a WrongStack session. It runs automatically when a session ends, and on demand. Trigger on the explicit vocabulary — "review", "code review", "quality check", "post-session review", "chimeric review", "chimera" — and on the task…
auto-review
Use this skill to configure and understand the built-in auto-review plugin (wstack-auto-review) that fires automated code review subagents on every code change during a session. Triggers: user says "auto review", "otomatik review", "auto code review", "her değişiklikte review", "/auto-review".
code-reviewer
Staff-engineer-level code review delivering 10 prioritized actionable findings across architecture, security, performance, and maintainability.
coderabbit-review
Use when you need to evaluate CodeRabbit PR comments and fix or reply.