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 pieable/dragon-ball-agent --skill code-reviewgit clone --depth 1 https://github.com/pieable/dragon-ball-agentWrote 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/pieable/dragon-ball-agent/code-review)<a href="https://agentmods.dev/skills/pieable/dragon-ball-agent/code-review"><img src="https://agentmods.dev/badge/skills/pieable/dragon-ball-agent/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/pieable/dragon-ball-agent/code-review"><img src="https://agentmods.dev/badge/skills/pieable/dragon-ball-agent/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 | $0.00063 | $0.03599 |
| Opus 5.5 | $0.00025 | $0.01440 |
| Sonnet 5.5 | $0.00013 | $0.00720 |
| Haiku 4.5 | $0.00006 | $0.00360 |
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 22d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
代码与文档评审
审查的目标是判断本次变更能否安全交付,而不是逐行挑错或替作者设计产品。先恢复实际变更和它必须满足的合同,再用与风险相称的深度取得证据。
评审对象和权限
评审结论只覆盖当前候选变更或指定文档及已经约定的要求,用于判断该候选能否合入或交付。它不代表整个用户任务已经完成,也不改变用户目标、产品路线或其他部分的设计。
代码候选评审开始前确认已有材料能够确定准确的基线和候选、变更应当产生的可观察结果、已接受的设计或约束、实际差异,以及已经取得的测试和运行证据。缺少会改变结论的内容时,补足材料或者给出“证据不足”,不猜测作者意图。单独核查已有文档时,明确文档对象、适用版本或核查时点,以及其重要主张的正确性依据,按相关内容补足实现、决定和验证材料。
审查主干
以下主干用于代码候选。纯文档任务按“文档正确性与进度同步”章节从用途、要求和原始依据开始核查,再按同一结论标准报告。代码、测试和运行记录按文档声明的需要取证。
- 确定对象。 核实比较的基线与候选版本、未提交改动和实际差异。目标变化后重新建立范围。只读足以理解设计的周边代码,不把一次审查扩展为全仓库审计。
- 恢复合同。 读取会决定结论的项目规则、接口、测试、文档、设计记录和调用方。恢复用户或系统可观察的结果、生产路径、必须保持或拒绝的不变量、已约定反例和通过门槛。区分已证实事实、作者主张与尚未验证的假设。
- 判断需求、设计和集成是否成立。 对照当前要求,检查候选是否遗漏必需行为、只完成一部分、产生相反结果,或增加未经确认且会改变结果、风险或维护负担的内容。先找出安全交付依赖的关键事实及权威实现位置,再追踪受影响行为从入口、调用方、状态与数据、外部边界到结果的关系,包括受影响但未出现在 diff 中的消费者、注册、发布和资料。对符号搜索难以覆盖的协议、存储格式、读取时序和库版本行为,沿实际实现核对。逐项追踪重要结果和不变量是否有实现位置及对应证据,确认设计和真实调用方能够共同实现目标行为,再深入局部细节。
- 按实际后果选择检查。 优先检查正确性、必需行为、数据保护、权限和生命周期,再考虑可维护性与风格。根据变更实际触及的机制深入相关风险,不机械跑固定清单。
- 验证证据强度。 核对证据是否对应当前候选,以及测试能否在目标错误出现时失败。预期应来自要求和真实接口,不能只复述实现或依赖作者自述。对拟报告的发现,主动核查可能推翻它的前置条件、调用方保证、框架处理、路径可达性和已接受的设计取舍;作者披露差异与合同负责人接受差异分别取证。保留有实际触发条件、因果路径和影响支撑的发现,按共同根因与所需纠正机制去重。对决定安全交付的关键事实,构造能推翻它的检查,核对实际代码或用户路径的相应证据,按下文要求处理缺口。测试、构建和静态检查只能证明各自覆盖的层级。任务要求真实宿主、加载器、界面、外部服务或模型调用时,确认是否已有该路径的可观察证据。没有时标明未验证,不把代理指标说成完成。
- 核对相关文档。 按下文的方法检查本次变更影响的文档是否正确、是否反映当前决定和实际进度,包括没有修改的相关资料。单独文档评审围绕指定对象及其依据执行同样的判断。
- 作出评审结论。 根据实际问题和证据强度,按下文的结论标准与报告要求交回结果。
局部、机械且结果唯一的改动可以轻量执行上述流程。功能、接口、状态或系统结构变更必须完成足以判断整体方向的审查。
验收追踪与门槛完整性
要求跨越多个组件、入口或外部边界时,检查每项重要结果和不变量从声明到实现再到证据是否闭合。证据在目标错误发生时应失败,并经过声明成立所依赖的边界。客户端限制不能证明服务端拒绝,内部函数测试不能证明 HTTP、CLI、模型或浏览器入口,分别满足局部限制不能证明组合后的最终预算或输出满足限制。
规格在实现期间变化时,确认受影响的计划、实现合同、测试和证据已经随之更新,未受影响部分没有被无故推翻。候选引用的要求与证据应属于同一当前规格和最终候选,不能混用已经被取代的要求或修改前证据。
检查反例和拒绝路径是否覆盖其他可执行入口、旧状态、重复请求和绕过方式。实现者新增局部测试不能替代既定门槛,也不能通过删除、跳过、放宽或改写门槛获得通过。门槛因真实要求、平台接口或新证据而改变时,确认改变由掌握验收合同的负责人作出,并重新判断受影响的证据。
交付候选的每项重要门槛应有明确状态。未执行、命令报错、结果待定和被跳过都不能算作通过;输出中的零失败也不能证明所有检查已成功执行。候选在取证后发生可能影响结论的变化时,要求补验受影响部分。
需要核对项目验证方式时,按 项目验证入口 检查已有操作入口、功能与检查的对应关系,以及本次合同涉及的路径。核对实例和版本、真实操作及副作用、清理后的证据留存。复用已有检查,缺少覆盖时在当前授权和只读边界内补取证据,无法补足的决定性缺口按“证据不足”处理。既有方式已足以证明结果时直接采用,完整应用实跑由结论所依赖的路径决定。
What ships with it
21 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 353 B
- evals/review-convergence.json 2.9 KB
- MODIFICATION_LOG.md 11 KB
- PROMPT_STRUCTURE.md 12 KB
- references/cases/mailparse-boundary-cost.md 989 B
- references/cases/openhands-profile-wording.md 1001 B
- references/cases/rclone-config-save.md 998 B
- references/cases/rclone-sftp-handle.md 940 B
- references/cases/sqlite-iterable.md 955 B
- references/cases/strata-draft-budget.md 1.1 KB
- references/cases/tauri-downstream-link.md 1.1 KB
- references/cases/vite-pending-css.md 799 B
- references/risk-index.md 1.9 KB
- references/risks/async-state-and-lifecycle.md 1.3 KB
- references/risks/budgets-and-complexity.md 1.9 KB
- references/risks/documents-and-product-semantics.md 1.6 KB
- references/risks/input-and-representation.md 1.0 KB
- references/risks/interfaces-and-integration.md 1.4 KB
- references/risks/model-protocol.md 1.4 KB
- references/risks/persistence-and-recovery.md 1.3 KB
- references/risks/scope-and-complexity.md 1.3 KB
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.
- 22d ago Changed · +2 lines 384de7cb3a1e
- 23d ago Changed · +30 lines · -2 tokens per session 16b9102bac6f
- 1mo ago Changed · +13 lines · +17 tokens per session 2f73a786709c
- 2mo ago Changed · +12 lines 6268f056aab4
- 2mo ago First seen · 50 lines · 48 tokens per session scan A 53c2564cef11
code-review is a skill published in the GitHub repository pieable/dragon-ball-agent (11 stars, last pushed 23d ago), licensed MIT. It adds 63 tokens to every session and 3,599 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.
code-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| code-reviewpieable/dragon-ball-agent | Skill | 11 | 23d ago | MIT | A | 63 | Codex |
| autoreviewopenclaw/clawhub | Skill | 9.5k | today | MIT | A | 17 | Claude Code, Codex |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 6d ago | MIT | A | 115 | Claude Code, Codex |
| omh-code-reviewrlaope/oh-my-hermes | Skill | 5.2k | yesterday | MIT | A | 48 | Claude Code, Codex |
| revdiff-planumputun/revdiff | Skill | 945 | 2d ago | MIT | A | 84 | Claude Code |
| explore-unknownsdzhng/skills | Skill | 1.4k | 2d ago | MIT | A | 162 | Claude Code, Codex |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | 4d ago | MIT | A | 70 | Claude Code |