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 skills/rpamis/comet/comet-verifynpx skills add rpamis/comet --skill comet-verifygit clone --depth 1 https://github.com/rpamis/cometWrote 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/rpamis/comet/comet-verify)<a href="https://agentmods.dev/skills/rpamis/comet/comet-verify"><img src="https://agentmods.dev/badge/skills/rpamis/comet/comet-verify.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.03446 |
| Opus 5 | $0.00015 | $0.01723 |
| Sonnet 5 | $0.00006 | $0.00689 |
| Haiku 4.5 | $0.00003 | $0.00345 |
Grade A, and why
comet-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 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comet 阶段 4：验证（Verify）
开始或恢复前必须先读取并执行 comet-classic/reference/classic-layout.md；本文件中的 OpenSpec CLI 调用必须使用 adapter，文件路径必须使用该协议绑定的 <classic-*> 逻辑根。
前置条件
- 代码已提交（阶段 3 完成）
- tasks.md 全部任务已完成
步骤
0a. 输出语言约束
验证报告必须使用 comet state get <name> language 读取到的 Comet 配置产物语言。
0b. 入口状态验证（Entry Check）
按 comet-classic/reference/scripts.md 使用稳定 comet CLI，然后执行入口验证；从任意入口恢复时先按 comet-classic/reference/context-recovery.md 运行恢复检查：
comet state select <change-name>
comet state check <change-name> verify
验证通过后继续 Step 1。验证失败时脚本会输出具体失败原因。
若上述 select / check 输出 BLOCKED，且原因是 bound_branch 与当前分支不一致，立即按 comet-classic/reference/decision-point.md 暂停，让用户单选：切回绑定分支后重新运行入口验证，或在用户明确确认当前分支应接管该 change 后运行 comet state rebind <change-name> 并重新入口验证。不得自行切换分支，不得自行换绑。
幂等性：verify 阶段所有检查可安全重复执行。如 verify_result 已为 pass，说明验证已完成并应进入 archive；branch_status 在归档提交和最终分支处理完成前保持 pending。如 verify_result 为 pending，从头开始验证。
1. 改动规模评估
执行规模评估：
comet state scale <change-name>
脚本自动统计任务数、增量规格数、变更文件数，判断使用 light 或 full 验证模式，并设置 verify_mode 字段。判定规则（满足任一即 full）：任务数 > 3、delta spec 能力数 > 1、变更文件数 > 8。
comet state scale 会自行从 plan 的 base-ref 解析提交基线，并在 plan 不可用时回退到状态中的 base_ref；Verify 不再重复读取 plan frontmatter 或手工拼接第二套规模评估。
验证开始前，按 comet-classic/reference/dirty-worktree.md 协议检查并处理未提交改动。verify 阶段的特殊处理：
- 若 dirty diff 明确属于当前 change，它就是本次验证输入；继续验证，但不在 verify 阶段修改或提交实现、测试、tasks、delta spec 或 Design Doc
- 若 dirty diff 只是 verify 本阶段产物（例如验证报告草稿），可继续在 verify 阶段完成并记录状态
- 若 dirty diff 显示实现已存在但 tasks.md 未勾选，视为 build 状态滞后；这是只有一个合法下一步的自动处理，运行
verify-fail返回 build 核对证据并更新任务状态，不得询问是否接受未完成任务 - 若 dirty diff 无法归因或属于其他 change，按 dirty-worktree 协议报告停止条件；不要把归因失败伪装成“继续/忽略”决策
需要回到 build 修复或补齐状态时运行：
comet state transition <change-name> verify-fail
覆盖机制：如 agent 或用户认为自动评估结果不合适，可随时通过 comet state set <change-name> verify_mode <light|full> 手动覆盖。
1b. 验证失败自动修复与例外决策
先运行 comet state get <change-name> verify_failures 读取已持久化的连续失败次数。前 3 次可修复失败自动回到 build：报告失败项后运行 comet state transition <change-name> verify-fail，再调用 /comet-build 修复，不需要用户确认。
What ships with it
1 file 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.
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 Changed · -10 lines a024d6bc8b36
- 4d ago First seen · 223 lines · 29 tokens per session scan A 73935e7a09e7
comet-verify is a skill published in the GitHub repository rpamis/comet (2,914 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 3,446 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
agent-spec-tool-first
CRITICAL: Use for agent-spec CLI tool workflow. Triggers on: agent-spec, contract, lifecycle, guard, verify, explain, stamp, checkpoint, plan, requirements, work-units, knowledge requirements, KLL, docs vs knowledge, spec verification, task contract, spec quality, lint spec, run log, "how to verify", "how to use…
agent-spec-authoring
CRITICAL: Use for writing and editing agent-spec .spec/.spec.md files. Triggers on: write spec, create spec, edit spec, new spec, spec authoring, task contract, .spec file, .spec.md file, BDD scenario, acceptance criteria, completion criteria, test selector, boundary, constraint, intent, decision, out of scope, "how…
agent-spec-estimate
CRITICAL: Use for estimating work effort from agent-spec Task Contracts. Triggers on: estimate, estimation, how long, work effort, round count, time estimate, scope, sizing, cost, budget, planning, sprint, capacity, "how many rounds", "how long will this take", "estimate this spec", 估算, 工作量, 多久, 时间估算, 预估, 工时, 规模…
agent-spec-intent-compiler
Use when converting PRD or issue prose into KLL requirements, running the intent compiler plan, or reverse-interviewing a human to resolve requirement ambiguity before task spec generation.
create-request
Create, update, or scan per-task request tickets for progress tracking. These are date-prefixed non-lifecycle docs under requests/, NOT feature-level requirements (use /req-analyze for those). Use when: tracking task progress, updating completion status, scanning incomplete requests, checking request status dashboard.…
codex-setup
Initialize sd0x-dev-flow infrastructure for Codex CLI and other non-Claude agents. Generates AGENTS.md, installs the commit-msg hook, copies runner scripts. The pre-push gate is opt-in via --with-push-gate. Use when setting up a new project or after updating skills.