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 agentmods add skills/rpamis/comet/comet-classicnpx skills add rpamis/comet --skill comet-classicgit 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-classic)<a href="https://agentmods.dev/skills/rpamis/comet/comet-classic"><img src="https://agentmods.dev/badge/skills/rpamis/comet/comet-classic.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 | $0.00053 | $0.05720 |
| Opus 5 | $0.00026 | $0.02860 |
| Sonnet 5 | $0.00011 | $0.01144 |
| Haiku 4.5 | $0.00005 | $0.00572 |
Grade A, and why
comet-classic 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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comet Classic — OpenSpec + Superpowers 双星开发流程
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。
OpenSpec 与 Superpowers 如双星系统围绕同一目标运转。
OpenSpec 负责 WHAT — 大纲、提案、spec 生命周期、归档
Superpowers 负责 HOW — 技术设计、计划、执行、收尾
核心原则:brainstorming 必不可跳过。每次变更都必须经过深度设计(hotfix 和 tweak 预设除外)。
决策核心(Decision Core)
agent 做决策只需读本节,参考附录按需查阅。
输出语言规则
所有 OpenSpec 和 Superpowers 产物都必须使用 Comet 配置的产物语言。配置值是规范化语言 ID,en 或 zh-CN。已有 change 优先通过 comet state get <name> language 读取 <classic-change-dir>/.comet.yaml 中的 language;.comet.yaml 尚不存在时依次读取项目 .comet/config.yaml 和全局 ~/.comet/config.yaml 的 classic.language;都不存在时才回退到当前用户请求语言。调用外部 OpenSpec/Superpowers skill 时,必须把解析后的语言显式写入 prompt 或 ARGUMENTS。
阶段自动检测
Step 0: 活跃 Change 发现与意图判定
- 先按
comet-classic/reference/scripts.md直接运行公开 Comet CLI 命令。 - 运行
comet classic openspec -- list --json获取所有活跃 change。 - 根据用户请求、active change 列表和必要仓库状态填写
CometIntentFrame。 - 优先用
comet classic intent route --stdin传入 frame JSON,获取 runtime 规范化路由。CometIntentFrame + runtime scorer是事实源;本节自然语言规则只用于意图识别槽位提取。 - 按 runtime route 处理:
hotfix→ 直接调用/comet-hotfixtweak→ 直接调用/comet-tweakfull→ 按活跃 change 表决定/comet-open或用户确认resume→ 进入 Step 1 读取对应 change 的.comet.yamlask_user→ 按comet-classic/reference/decision-point.md暂停并等待用户选择out_of_scope→ 说明本次输入不是 Comet workflow 启动/恢复请求,不初始化 change
当 runtime route、Ambient Resume 或用户选择已经解析出明确 change 后,进入对应阶段 Skill 前必须先绑定当前执行上下文:
comet classic workspace resolve <change-name> --json
# 进入返回的 projectRoot;state select 会在该工作区写入选择
comet state select <change-name>
新 change 的 workspace 决策在 /comet-open 完成,并遵循 comet-classic/reference/workspace.md:用户明确表达并行、同时处理或多个会话时,在绑定前准备 Worktree;未指定隔离方式时,需要决策就把 current、branch、worktree 作为单选项展示,推荐只作说明。准备和恢复都会扫描已登记 Worktree,优先复用分支匹配的工作区;当分支已重命名、被用户接管或无法确认归属时请求 rebind。
多个 active change 且用户尚未明确选择时,不得提前绑定;继续按 ask_user 决策点等待选择。
What ships with it
13 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.
- agents/openai.yaml 112 B
- reference/auto-transition.md 1.3 KB
- reference/classic-layout.md 2.4 KB
- reference/comet-yaml-fields.md 6.8 KB
- reference/context-recovery.md 2.9 KB
- reference/debug-gate.md 2.3 KB
- reference/decision-point.md 3.0 KB
- reference/dirty-worktree.md 3.2 KB
- reference/file-structure.md 1.4 KB
- reference/intent-frame.md 4.5 KB
- reference/scripts.md 3.2 KB
- reference/subagent-dispatch.md 15 KB
- reference/workspace.md 1.9 KB
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 · +2 lines 072d91b8e453
- 5d ago First seen · 290 lines · 53 tokens per session scan A ac122f46f2d2
comet-classic is a skill published in the GitHub repository rpamis/comet (2,914 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 5,720 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 2026-08-30.
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
Requirements analysis — problem decomposition, stakeholder scan, requirement structuring. Produces 1-requirements.md (Phase 1 lifecycle doc, NOT the per-task request ticket — for those use /create-request). Use when: analyzing needs before tech spec, decomposing requirements, stakeholder analysis, 需求分析. Not for…
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).
jira
Jira integration — view issues, generate branches, create tickets, transition status. Use when: user mentions Jira ticket key (XX-123), says /jira, wants to create branch from ticket, create a new ticket, or update Jira status. Not for: GitHub issues (use issue-analyze).