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 Shy2593666979/AgentChat --skill code-reviewgit clone --depth 1 https://github.com/Shy2593666979/AgentChatWrote 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/shy2593666979/agentchat/code-review)<a href="https://agentmods.dev/skills/shy2593666979/agentchat/code-review"><img src="https://agentmods.dev/badge/skills/shy2593666979/agentchat/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/shy2593666979/agentchat/code-review"><img src="https://agentmods.dev/badge/skills/shy2593666979/agentchat/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 | $0.00041 | $0.00354 |
| Opus 5.5 | $0.00016 | $0.00142 |
| Sonnet 5.5 | $0.00008 | $0.00071 |
| Haiku 4.5 | $0.00004 | $0.00035 |
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 yesterday.
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
代码审查
围绕用户指定的变更范围审查。需要上下文时，说明缺少的调用方、模型或测试信息，不把未知情况当作已确认缺陷。
工作方法
- 概括变更目的和受影响的行为，明确实际收到的是完整文件还是差异片段。
- 沿输入、状态变化与输出核对逻辑。重点关注空值、错误路径、并发、资源释放、权限边界及接口兼容性。
- 对每个候选问题寻找具体触发条件与证据。已由调用方或类型约束排除的问题不报告为缺陷。
- 按影响排序发现项，说明位置、触发方式、后果与最小修复方向。不能定位行号时使用函数名或代码片段，不虚构位置。
- 给出针对行为的验证方法。纯风格偏好放在可选建议，不与功能问题混排。
使用 /code-review/reference/output-template.md 输出发现项；交付前读取 /code-review/reference/review-checklist.md。
能力边界
当前只能审查实际提供的代码与技能文件，不具备访问用户代码仓库或执行测试的能力。不要声称运行过测试或检查过未提供的文件。没有发现有依据的缺陷时直接说明，并列出实际审查范围。
What ships with it
3 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.
- yesterday First seen · 23 lines · 41 tokens per session scan A 1924cde684e2
code-review is a skill published in the GitHub repository Shy2593666979/AgentChat (921 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 354 once invoked, about $0.0002 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 2026-10-18.
Other skills, from other repositories
simplify-code
Sequential 3-lens cleanup of recent code changes.
error-recovery
A guide to detecting and recovering from failures in long-running AI agents. It covers API outages, bad tool calls, broken conversation state, stalled streams, repeated loops, retries, fallback models, and circuit breakers that stop repeated failure.
redos
Hunt ReDoS (CWE-1333, Catastrophic Backtracking) — identify regexes with nested quantifiers or overlapping alternation that cause super-linear matching time, trace tainted input paths to regex sinks, demonstrate timing PoC, and validate with response-time delta. Covers PCRE/RE2/V8/Python re engine differences.…
seven-question-gate
7-question gate run before promoting a finding to FINDING + opening a report. Kills weak/non-impactful findings before they reach the report stage and damage validity ratio.
pattern-exhaustion
Systematic pattern exhaustion methodology. Load after finding any confirmed vulnerability to search for all instances of the same root cause pattern across the codebase.
scanner-overview
Stage 1 broad-spectrum scanner playbook. Sharded sweep over very large codebases producing CANDIDATE nodes for the Detector to reason about. Load at scanner-agent startup.