Comet is a resumable workflow and skill platform for coding tasks, covering requirements work as well as skill creation, evaluation, and release. It supports separate Native and Classic workflows and can coordinate implementation and verification across isolated Git worktrees. The catalogue contains skills and instructions that implement Comet-related workflows.
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 rpamis/comet --skill applicationgit 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/application)<a href="https://agentmods.dev/skills/rpamis/comet/application"><img src="https://agentmods.dev/badge/skills/rpamis/comet/application/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/rpamis/comet/application"><img src="https://agentmods.dev/badge/skills/rpamis/comet/application.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 | $0.00033 | $0.01418 |
| Opus 5.5 | $0.00013 | $0.00567 |
| Sonnet 5.5 | $0.00007 | $0.00284 |
| Haiku 4.5 | $0.00003 | $0.00142 |
Grade A, and why
grill-test 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 yesterday.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grill Test
用户明确选择这条链路时使用。先读取执行与恢复，沿同一 SDK 根 Run 和当前子 Run 执行。
原始 Skill 的职责
-
grill：加载固定的 grill-me 原文；它仅要求执行 grilling 会话，没有文件输出。
立即执行： 使用 Skill 工具加载 grilling 技能。禁止跳过此步骤。
技能加载后，按原始 design tree/frontier 规则访谈。环境事实由子 Agent 调查，实际决定询问用户并等待回答。frontier 为空后，请用户确认共同理解。保留真实会话，并将会话摘要回传 SDK grill Action；通过该子 Run 的 confirm-understanding Wait 保存理解确认。此阶段不创建 brief 或其他业务文档，不借用 Native 的阶段产物。
-
to-spec：读取固定的 to-spec 原文，综合已确认的会话和代码事实，不再次访谈已有决定。按原模板七个章节生成第一份正式文档，确认测试 seams，发布至本地 tracker 的 .scratch/grill-test/spec.md。通过 confirm-spec 保存实际确认。
-
to-tickets：读取固定的 to-tickets 原文，展示 tracer-bullet 切片、粒度和 blocking edges，取得用户决定后按原模板一票一文件写入 .scratch/grill-test/issues/，使用 ready-for-agent 标签。tickets.json 仅是本应用为核对实际文件和依赖而保存的索引，不是原 Skill 自带的产物。通过 confirm-tickets 保存实际确认。
-
implement：根 Run 的 authorize-implementation 获批后，读取固定 implement 原文。按已批准票据实现，使用 tdd 在约定 seams 验证，执行相关检查与最终完整业务测试，按 code-review 原文开展 Standards/Spec 双轴子 Agent 审查，只在隔离项目本地提交。implementation.json 是应用的执行记录，不称为原 Skill 的产物。
grill-me、to-spec、to-tickets、implement 的原文件含 disable-model-invocation，宿主无法嵌套调用时读取当前包固定原文，并如实记录文件加载；grilling、tdd、code-review 可用时必须通过实际 Skill 工具加载。不修改原始 Skill 的 frontmatter 或正文。
验收与恢复
输入为 goal、acceptance[{id,description}] 和 testCommand 数组；本地 tracker 由用户事先选择。所有业务检查使用原测试命令；verify 的机器执行端口真实运行测试，验证器只读检查结果。独立 Eval 另外运行原始测试，不能以报告或字符串代替任务完成。
获批 Spec 与票据在实现阶段保持只读。真实批准或 Skill 能力缺失时停在当前步骤，保留原 Run；running/unknown 先核对宿主和实际结果。只使用当前 Action/Wait 身份，不伪造会话回答、批准或成功状态。只有实际 SDK 根 Run completed、业务测试通过且评审证据可查，才能报告业务任务完成。
凭据仅留在执行环境。固定应用、SDK 状态、安装目录由正式 Runtime 维护。本应用不授权远端 Issue、PR、推送、发布或真实消息。
四个阶段都在 SDK 子流程中保留原 Skill 的执行职责；根 Run 的 authorize-implementation 仍在 implement 子流程启动前确认实现范围。应用 Guard 只允许已领取子 Action 的实际阶段产物，grill 无业务文件范围。
SDK 执行协议
固定组合：e0a776e8c9940ecf07ee97c8399d4500bdaa6889e717966487c075ef33a19fa5 Runtime：0.5.0；基础流程：standalone。
用 comet runtime dispatch --application-file <本目录>/application.json --project-root <项目> --request <临时JSON> 启动下列流程：
- grill-test@3
- grill-me@1
- to-spec@1
- to-tickets@1
- implement@1
What ships with it
30 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.
- application.json 14 KB
- application.mjs 5.3 KB runs code
- bindings.mjs 8.8 KB runs code
- installation.json 2.1 KB
- references/execution.md 2.5 KB
- rules/workflow-guard.md 7.1 KB
- skills/code-review/agents/openai.yaml 103 B
- skills/code-review/SKILL.md 6.6 KB
- skills/grill-me/agents/openai.yaml 142 B
- skills/grill-me/SKILL.md 154 B
- skills/grilling/agents/openai.yaml 116 B
- skills/grilling/SKILL.md 1.8 KB
- skills/implement/agents/openai.yaml 144 B
- skills/implement/SKILL.md 448 B
- skills/setup-matt-pocock-skills/agents/openai.yaml 157 B
- skills/setup-matt-pocock-skills/domain.md 2.0 KB
- skills/setup-matt-pocock-skills/issue-tracker-github.md 3.7 KB
- skills/setup-matt-pocock-skills/issue-tracker-gitlab.md 3.8 KB
- skills/setup-matt-pocock-skills/issue-tracker-local.md 1.8 KB
- skills/setup-matt-pocock-skills/SKILL.md 6.9 KB
- skills/setup-matt-pocock-skills/triage-labels.md 1.0 KB
- skills/tdd/agents/openai.yaml 90 B
- skills/tdd/mocking.md 1.5 KB
- skills/tdd/SKILL.md 3.5 KB
- skills/tdd/tests.md 2.2 KB
- skills/to-spec/agents/openai.yaml 140 B
- skills/to-spec/SKILL.md 3.0 KB
- skills/to-tickets/agents/openai.yaml 151 B
- skills/to-tickets/SKILL.md 5.7 KB
- tools/session.mjs 4.4 KB runs code
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.
- yesterday First seen · 63 lines · 33 tokens per session scan A c4bf61828645
grill-test is a skill published in the GitHub repository rpamis/comet (3,227 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 1,418 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 2026-10-23.
Other skills, from other repositories
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.…
req-analyze
A requirements-analysis tool that breaks a problem into needs, stakeholders, and priorities before a technical solution is chosen.
feature-verify
Feature verification (READ-ONLY, P0-P5). Use when: verifying feature behavior after deployment, validating API responses, diagnosing production issues, post-deploy smoke test. Not for: modifying data (use feature-dev), code review (use codex-review-fast), writing tests (use codex-test-gen), security audit (use…
recap-ask
Interactive Q&A over an existing recap document. Use when: user wants to ask follow-up questions about a briefing-recap- .md produced by /recap-doc, with recap-bounded context + out-of-scope redirect + optional promote-to-request. Not for: generating a new recap (use /recap-doc), general project Q&A (use /ask), code…
recap-doc
Post-development recap document generator. Use when: AI/Codex has implemented a feature and the user needs a guided walkthrough of what changed and why, with blind-spot detection and anticipated questions. Not for: Q&A follow-up (use /recap-ask), technical share-out for teammates (use /tech-brief), or generic code…
runbook
Generate and update feature release runbooks from existing docs and codebase. Use when: creating operational runbook, release handbook, deployment checklist, pre-release preparation. Not for: incident response (v2), code review (use codex-code-review), architecture design (use architecture).