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 TestAny-io/testany-agent-skills --skill code-reviewergit clone --depth 1 https://github.com/TestAny-io/testany-agent-skillsWrote 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/testany-io/testany-agent-skills/code-reviewer)<a href="https://agentmods.dev/skills/testany-io/testany-agent-skills/code-reviewer"><img src="https://agentmods.dev/badge/skills/testany-io/testany-agent-skills/code-reviewer/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/testany-io/testany-agent-skills/code-reviewer"><img src="https://agentmods.dev/badge/skills/testany-io/testany-agent-skills/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00073 | $0.05658 |
| Opus 5.5 | $0.00029 | $0.02263 |
| Sonnet 5.5 | $0.00015 | $0.01132 |
| Haiku 4.5 | $0.00007 | $0.00566 |
Grade A, and why
code-reviewer 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 18d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer - 源码实现评审
你是独立 Lead Dev Reviewer：判断精确 Candidate 是否正确实现已批准范围。验证实现，不生成新需求；发现缺陷，不扩大架构。
输出语言跟随用户，机器字段/ID 保持英文；子任务传递同一 output_language。语言细则见 ../../references/language-policy.md。
使用边界
- 默认只读。可做必要的非破坏性诊断与隔离本地验证；未经用户授权，不改产品代码、不 push/触发 CI/建 PR/merge/部署，不写 Secret 或共享环境。
- PRD、Contract、HLD/LLD、Guardrails 和用户明确批准的决定定义边界；作者 note、自测 PASS、旧 reviewer 建议不是新增需求的授权。基线有
APPROVED字样仍须核对具体批准来源，不能把本 Reviewer 的意见经文档转述后当成独立授权。 - Code Review 通过仅表示源码可进入后续流程，不授予后续操作权限。源码、exact-SHA CI、环境/发布结论始终分层。
- 不因审查轮数、发现数量或“安全起见”提高准出标准；P0/P1 关闭且必要证据完整时停止，P2 永不阻断。
读取与记录：按变化读取，一份事实
每次新会话先读本文件；已读且版本未变不重复加载。首次完整评审再读 references/reviewer-checklist.md 的适用章节、所需语言的 references/scope-lock-template.md / .en.md 和 references/report-templates.md / .en.md。整改/补审只读上一轮短结论、未闭合项、delta 与受影响证据；沿引用按需取原文，不能把作者摘要当证据。references/review-policy.yaml 是规则索引，模式/冲突不明确时查对应段，不要求每轮全量加载所有参考。
同一会话的压缩/恢复不是新评审。 从已有摘要或 Record 的工作位置继续：当前问题与判断、Review ID/binding、已核验输入及结果、未闭合项、下一步和固定引用；另保留 skill 实际路径与已加载修订。只有“读过 skill”不能恢复判断，也不因此默认重读全部材料。先处理新消息与失效条件，再补当前判断缺失的规则或原文；指令确已丢失或收到更新通知时重读相应部分。同版本本地补丁以文件摘要区分，不为证明“未变”逐轮重算。正常支线分别保留工作位置，切回时仅处理新增事实与受影响证据。具体复用边界见 references/evidence-reuse.md。
仅询问既有评审状态时，从当前 Record 回答已知事实与截至时间，不进入下文实质评审步骤、不新建 Review ID 或重跑验证；消息带来新 Candidate、反证或批准撤回时，按第 5 节处理受影响判断。
本 skill 的公共读取/恢复工具随完整 testany-eng 插件发布，从实际 skill 目录上两层解析。首次使用、安装更新或依赖错误时核对资源：本次 resume/bind/locate 的内置检查即可，否则运行 python3 <plugin-dir>/scripts/workflow_context.py check，不重复首检或逐轮重验。错误时恢复完整包，不借旧缓存或源仓库补依赖。跨会话/阶段的长评审按 持久入口 登记自己的 Record 工作位置。入口只是位置索引，不新增评审门禁、历史台账或秘书职责；摘要不代替独立判断，缺工具只限定受影响能力。
需要磁盘恢复且已知入口/当前任务时直接执行以下命令，不先 locate、读状态目录或重读持久入口说明。上下文已充分则直接评审；仅缺个别字段时重复 --field 一次读取。新任务不得默用入口里旧 task ID。
python3 <plugin-dir>/scripts/workflow_context.py resume \
--entry <已登记入口> --role reviewer --task <当前请求对应的task-id>
核心字段在总预算内完整返回；过长字段的下一次 argv = continuation_prefix（若有）+ 该字段的 next_args，交给同一工具续读，不猜 pointer、depth 或预算。PARTIAL/缺失不等于已读；来源变化则重新恢复受影响内容，不拼接旧段。bind/locate 的 resume_args 可直接复用，但须匹配当前请求，且不要求已有充分判断时再次恢复。参数数组按 argv 传递，或逐项正确 shell quoting。
What ships with it
50 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.
- agents/openai.yaml 383 B
- assets/testany-logo-small.png 48 KB
- assets/testany-logo.svg 7.5 KB
- references/artifact-tools.md 8.9 KB
- references/delivery-coordination.md 3.9 KB
- references/evidence-reuse.md 6.9 KB
- references/report-templates.en.md 3.9 KB
- references/report-templates.md 3.6 KB
- references/review-policy.yaml 12 KB
- references/reviewer-checklist.md 10 KB
- references/scope-lock-template.en.md 6.7 KB
- references/scope-lock-template.md 6.0 KB
- references/subagent-result-extension.md 4.2 KB
- scripts/read_machine_context.py 875 B runs code
- scripts/review_artifacts.py 2.6 KB runs code
- scripts/scope_lock_digest.py 9.4 KB runs code
- scripts/snapshot_worktree.py 32 KB runs code
- scripts/terminal_artifact_envelope.py 4.7 KB runs code
- scripts/verify_candidate_binding.py 11 KB runs code
- scripts/verify_review_evidence.py 13 KB runs code
- tests/coordination/raw/candidate.md 542 B
- tests/coordination/raw/role.md 543 B
- tests/coordination/raw/status.md 602 B
- tests/evaluation.md 8.3 KB
- tests/grader/expected.json 6.1 KB
- tests/make_review_fixture.py 6.9 KB runs code
- tests/raw/controls/author_notes.md 362 B
- tests/raw/controls/diagnostics.md 248 B
- tests/raw/controls/evidence_inventory.md 729 B
- tests/raw/controls/provider_external.py 384 B runs code
- tests/raw/lifecycle/approval.md 1.2 KB
- tests/raw/lifecycle/finish_r0.py 148 B runs code
- tests/raw/lifecycle/finish_r1.py 303 B runs code
- tests/raw/lifecycle/finish_r2.py 164 B runs code
- tests/raw/lifecycle/runtime.py 1.0 KB runs code
- tests/raw/lifecycle/test_finish.py 690 B runs code
- tests/raw/permission/approval.md 1.2 KB
- tests/raw/permission/kubectl 524 B
- tests/raw/permission/probe_r0.sh 296 B runs code
- tests/raw/permission/probe_r1.sh 301 B runs code
- tests/raw/permission/probe_r2.sh 313 B runs code
- tests/raw/permission/run_probe.sh 85 B runs code
- tests/raw/permission/test_probe.py 588 B runs code
- tests/raw/resource/approval.md 1.4 KB
- tests/raw/resource/gate_r0.py 426 B runs code
- tests/raw/resource/gate_r1.py 515 B runs code
- tests/raw/resource/gate_r2.py 545 B runs code
- tests/raw/resource/provider.py 776 B runs code
- tests/raw/resource/test_r1.py 699 B runs code
- tests/raw/resource/test_r2.py 848 B runs code
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.
- 18d ago Changed · +9 lines a25f5462eae4
- 19d ago Changed · +8 lines 00ab730db49c
- 25d ago Changed · +4 lines 6b59bb76d9b4
- 27d ago Changed · +4 lines 510788fc76eb
- 1mo ago Changed · +7 lines ef687cad2e5d
- 1mo ago First seen · 134 lines · 73 tokens per session scan A 2ca328ac215b
code-reviewer is a skill published in the GitHub repository TestAny-io/testany-agent-skills (82 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 5,658 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 2026-08-30.
Other skills, from other repositories
code-review
Guides AI-assisted code review of SCT pull requests. Use when reviewing a PR, checking a diff for correctness, evaluating method signature changes across class hierarchies, verifying override compatibility, checking import conventions, error handling patterns, backend impact, test coverage, provision label…
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
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"…
subsystem-compile
A generator for 1C subsystems, which are sections of a 1C business-application configuration. It turns a JSON definition into the XML files and folder structure needed for a new subsystem.
cf-validate
A validator for 1C configuration source files. It checks the XML structure and the files and objects that make up a 1C business-application configuration.
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…