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 Jerrylalala/compound-engineering --skill review-contractgit clone --depth 1 https://github.com/Jerrylalala/compound-engineeringWrote 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/jerrylalala/compound-engineering/review-contract)<a href="https://agentmods.dev/skills/jerrylalala/compound-engineering/review-contract"><img src="https://agentmods.dev/badge/skills/jerrylalala/compound-engineering/review-contract/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/jerrylalala/compound-engineering/review-contract"><img src="https://agentmods.dev/badge/skills/jerrylalala/compound-engineering/review-contract.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 | $0.00061 | $0.02226 |
| Opus 5 | $0.00030 | $0.01113 |
| Sonnet 5 | $0.00012 | $0.00445 |
| Haiku 4.5 | $0.00006 | $0.00223 |
Grade A, and why
review-contract 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 8d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Contract — Fork Overlay
基础层：上游
ce:review已实现 P0-P3 严重级别、confidence 阈值（≥0.60 才报告）、autofix_class 路由。本 Overlay 增量：三档 Tier 分类 + 对应的 anti-leniency 强度 +
conclusion_type覆盖层。
Tier 分类
命名规范：
[上游]= 在skills/ce-review/references/persona-catalog.md中有记录，由 ce:review 编排器实际派发。[本地]= 仅在agents/review/中存在但不在 persona-catalog，需手动调用，不被编排器自动派发。
| Tier | Agents | Anti-Leniency 强度 |
|---|---|---|
| Blocking | security-reviewer [上游], data-migrations-reviewer [上游], deployment-verification-agent [上游] |
零容忍：confidence ≥ 0.50 且 severity P0 必须报告，不确定时用 needs-human-check |
| Analytical | architecture-strategist [本地], performance-reviewer [上游], kieran-rails-reviewer [上游], kieran-typescript-reviewer [上游], kieran-python-reviewer [上游], julik-frontend-races-reviewer [上游], dhh-rails-reviewer [上游], pattern-recognition-specialist [本地] |
严格务实：必须提供触发条件/复现场景；没有场景的担忧降级为 question |
| Advisory | code-simplicity-reviewer [本地], agent-native-reviewer [上游], schema-drift-detector [上游] |
建议为主：默认 autofix_class: advisory，除非与明确 spec/CLAUDE.md 冲突 |
已更正的名称对照（原名 → persona-catalog 名）：
security-sentinel→security-reviewerdata-integrity-guardian+data-migration-expert→data-migrations-reviewer（合并，上游统一入口）performance-oracle→performance-reviewer
结论类型系统（conclusion_type 覆盖层）
注意：
conclusion_type是本 overlay 新增的本地语义字段，不存在于上游 findings-schema.json。 上游 schema 使用autofix_class、severity、confidence等字段。 本字段仅在此 overlay 内部使用，不写入上游 schema。
上游 schema 已有 autofix_class 路由。本 overlay 增加一个更语义化的 conclusion_type 字段，与上游字段并存：
conclusion_type |
映射关系 | 何时使用 |
|---|---|---|
finding |
上游 P0/P1/P2 + confidence ≥ 0.70 | 有确凿证据的问题，有代码引用 |
question |
上游 residual_risks / confidence 0.60-0.69 |
不确定，需要讨论 |
needs-human-check |
上游 requires_verification: true |
超出 AI 判断能力 |
clear |
上游 findings 为空 | 此项无问题 |
Anti-Leniency 参考原则（仅供分类框架参考）
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.
- 8d ago First seen · 155 lines · 61 tokens per session scan A 62abf7effc9f
review-contract is a skill published in the GitHub repository Jerrylalala/compound-engineering (5 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 2,226 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…