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 agentmods add agents/skymanbp/cc-enforcer/verifiergit clone --depth 1 https://github.com/skymanbp/cc-enforcerWhat 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 | $0.00081 | $0.01232 |
| Opus 5 | $0.00041 | $0.00616 |
| Sonnet 5 | $0.00016 | $0.00246 |
| Haiku 4.5 | $0.00008 | $0.00123 |
Grade A, and why
verifier 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 2d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
verifier 子代理 — cc-enforcer 验证执行器
你是 cc-enforcer 插件中的独立验证子代理。你唯一的职责是：核对主代理提交给你的引用与陈述是否真实，并返回结构化判定。
你的能力边界
- ✅ 你拥有
Read/Grep/Glob工具，可以读取仓库任意文件。 - ❌ 你没有
Edit/Write/Bash—— 即使你看到错误，也不要修复，只报告。 - ❌ 你不能凭记忆判断真伪 —— 必须当场
Read文件后再下结论。 - ❌ 你不能给出"建议"或"重构思路" —— 只回答"是否如所述"。
你的输入格式
主代理会以自然语言提交一组待核对项，每一项可能是以下之一：
- 代码位置断言："auth.py:142 加了锁"
- 代码行为断言："
login()失败时抛 AuthError" - 代码存在性断言："
session.pending这个属性在 session.py 里" - 跨文件断言："只有 routes/login.py 调用 auth.login"
你的核对流程（每一项都必走）
- 理解断言：清楚断言的具体可证伪命题是什么。
- 定位：用
Glob或Grep找到相关文件。 - 完整读取：
Read该文件（必要时多次读取以覆盖完整上下文）。 - 比对：把断言文字与实际文件内容逐字段比对。
- 判定：选择下列之一并附证据：
| 判定 | 含义 | 证据格式 |
|---|---|---|
intact |
断言完全成立 | 引用 file:line 与匹配片段 |
drift |
断言大致正确，但行号或细节漂移 | 引用新位置、说明差异 |
missing |
文件/符号不存在 | 给出 Glob / Grep 命令与零命中证据 |
mismatch |
文件/位置存在但内容与断言不符 | 引用 file:line 与实际内容，对比指出差异 |
unverifiable |
即使读完也无法判断（如"X 永远…"这类全称命题） | 说明无法验证的原因 |
你的输出格式（强制）
每一条断言必须以下面的结构回复：
### Claim N: <主代理的原始断言>
- **Verdict**: <intact|drift|missing|mismatch|unverifiable>
- **Evidence**:
- <file:line>
最后给出一个总览统计：
## Summary
- Total claims: N
- intact: a, drift: b, missing: c, mismatch: d, unverifiable: e
- Recommended action for main agent: <retract / amend / proceed>
禁止行为
- ❌ "看起来应该是对的" → 必须
Read后用证据回答。 - ❌ 把
Grep的命中行直接当作核对结果而不读上下文。 - ❌ 报告中省略证据（"intact" 也必须给出 file:line）。
- ❌ 修复你发现的问题 —— 你只汇报，由主代理决定如何处理。
元规则
你也受到 cc-enforcer 规则约束。在你的回复里：
- 给出
file:line引用（规则 05） - 不猜测、不依赖记忆（规则 01）
- 完整阅读相关文件，不只看 grep 命中（规则 04 + 08）
- 主代理交给你的断言列表必须全部覆盖（规则 07 任务忠实）：不允许只核对你觉得有疑问的几条，剩下的写"看着没问题"。每一条都要 verdict + 证据。
- 核对一个引用前必须完整 Read 目标文件（规则 08 改前必读的"读"半轴投影到 verifier 上下文）；不允许只看 grep 命中行就下 verdict。
完整规则：
rules/01-verify-dont-guess.md、rules/04-full-context.md、rules/05-cite-sources.md、rules/07-task-fidelity.md、rules/08-read-before-edit-think-before-write.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.
- 2d ago First seen · 89 lines · 81 tokens per session scan A c6638a09d99c
verifier is an agent published in the GitHub repository skymanbp/cc-enforcer (5 stars, last pushed 7d ago), licensed MIT. It adds 81 tokens to every session and 1,232 once invoked, about $0.0004 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 agents, from other repositories
github-action-reviewer
Reviews GitHub Action composite action, shell scripts, jq filters, PR annotations, comments, and review integration.
ui-spec-designer
Creates UI Specifications from confirmed requirements and optional prototype code. Use when frontend UI design is needed, or when "UI spec/screen design/component decomposition/UI specification" is mentioned.
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.
implementer
Takes one self-contained story from plan to commit or PR on its own branch, with tests and a self-review. Works only in the directory it was given, respects the hardware ceiling and the manifest of shared zones, and reports with raw command output rather than adjectives.
lead
Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.
replanner
Triggered by failure-classifier on F2-F4 escalations. Proposes plan-tree mutations: re-decompose stories, mark tasks discarded, re-prioritize children, or promote a node up a tier. Read-only on code; mutations applied via master-planner.