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.
git clone --depth 1 https://github.com/skymanbp/cc-enforcerWrote 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/commands/skymanbp/cc-enforcer/verify)<a href="https://agentmods.dev/commands/skymanbp/cc-enforcer/verify"><img src="https://agentmods.dev/badge/commands/skymanbp/cc-enforcer/verify/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/commands/skymanbp/cc-enforcer/verify"><img src="https://agentmods.dev/badge/commands/skymanbp/cc-enforcer/verify.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 | $0.00028 | $0.00894 |
| Opus 5.5 | $0.00011 | $0.00358 |
| Sonnet 5.5 | $0.00006 | $0.00179 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
verify 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 1mo 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
/cc-enforcer:verify
触发独立验证流程。要求 receiving agent 把"自己刚才说过的话"当作不可信输入重新核对。
你（receiving agent）要做的事
针对最近一次回复中所有事实性陈述，逐条执行下列流程：
第 1 步 · 列出所有"声明"
提取最近回复中的每一条事实性断言，并按下面四类分桶：
- 代码位置断言（如 "auth.py:142 加了锁"）
- 代码行为断言（如 "调用 X 会触发 Y"）
- 外部资源断言（如 "PEP 484 规定…"、"该库版本 1.2.0 引入了…"）
- 运行结果断言（如 "测试通过"、"命令输出 …"）
第 2 步 · 逐条核对
| 类别 | 核对方式 |
|---|---|
| 代码位置 | 委派 verifier 子代理 (Agent tool, subagent_type="verifier") 重读 file:line 并比对内容 |
| 代码行为 | Read 完整函数 + 调用链；如必要 Grep 调用方；不能仅凭函数名推断 |
| 外部资源 | 如有 URL：WebFetch；如有 DOI/章节：用户授权后访问；不能凭记忆 |
| 运行结果 | 重新运行同样的命令并粘贴新输出；不能复述"上次运行的结果" |
第 3 步 · 报告
输出一份结构化报告：
## Verify report
### 代码位置（共 N 条）
- [✅ intact ] auth.py:142 — 内容与声明一致 (verifier 已确认)
- [⚠ drift ] session.py:88 — 行号已变成 91 (代码近期被修改)
- [❌ missing] db.py:200 — 文件只有 178 行
### 代码行为（共 M 条）
- [✅ verified] login(...) 确实在失败时抛 AuthError (auth.py:155-160)
- [❓ unverified] "session_token 全局唯一" 这一断言我无法在代码中找到证据 — 撤回该断言
### 外部资源（共 K 条）
- [✅ verified] PEP 484 §"Type aliases" 确实如所述
- [❌ guessed] "redis-py 5.0 默认开启 connection pooling" — 我没有验证；撤回
### 运行结果（共 L 条）
- [✅ rerun] pytest tests/test_auth.py: 21 passed (粘贴新输出)
- [⚠ stale] 我之前说"npm test 通过"，但本次重跑前我没有再次确认 — 现在重跑：[结果]
第 4 步 · 修正
报告里任何 drift / missing / unverified / guessed / stale 条目：
- 如果是事实错误 → 立即在后续回复中明确撤回并提供正确版本；
- 如果是行号漂移 → 给出新行号；
- 如果原本就无法验证 → 明确说明"该断言无法验证，撤回"。
禁止行为
- ❌ 把
/cc-enforcer:verify当成形式主义、所有条目都标 ✅ 而不真做工具调用。 - ❌ 用"我相信刚才说的没问题"当作核对结果。
- ❌ 跳过"重新运行命令"那一步。
详见
rules/01-verify-dont-guess.md与rules/05-cite-sources.md。
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.
- 1mo ago First seen · 74 lines · 28 tokens per session scan A bac92d588222
verify is a command published in the GitHub repository skymanbp/cc-enforcer (6 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 894 once invoked, about $0.0001 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.
Other commands, from other repositories
debug
Systematic debugging: root cause before any fix, one hypothesis at a time, and a three-strikes rule that questions the architecture instead of stacking patches.
lint
The canonical linter per ecosystem over your changes: findings are diagnoses you judge, fix, or explain.
sm-refit
Run slop-mop's one-time onboarding remediation rail for this repository.
logic-fix-all
Autonomous audit-and-fix — after consent, scan the target, fix every logic issue found (all severities), verify each fix, and report anything unresolved.
logic-explain
Trace execution step by step — use when code behavior is surprising or confusing.
logic-health
Sweep a whole codebase or directory for logic correctness — use before a release or to identify risk hotspots.