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 comet-opengit 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-open)<a href="https://agentmods.dev/skills/rpamis/comet/comet-open"><img src="https://agentmods.dev/badge/skills/rpamis/comet/comet-open/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/comet-open"><img src="https://agentmods.dev/badge/skills/rpamis/comet/comet-open.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Prompt Injection · line 67 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 67 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.05714 |
| Opus 5.5 | $0.00013 | $0.02286 |
| Sonnet 5.5 | $0.00007 | $0.01143 |
| Haiku 4.5 | $0.00003 | $0.00571 |
Grade A, and why
comet-open 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 3d 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comet 阶段 1：开启（Open）
首次进入阶段、交接给新 Agent 或上下文恢复后，读取并执行 任务上下文与产物语言，优先采用当前 continuation 或已领取 Action 的 contextRequest；同一阶段连续执行不重复获取。
开始或恢复任务前，必须先读取并遵守 comet-classic/reference/classic-layout.md。本文件中的 OpenSpec CLI 调用必须通过适配器执行，文件路径必须基于该协议绑定的 <classic-*> 逻辑根目录。
前置条件
- 无活跃 change，或用户希望创建新 change
步骤
0. 设置输出语言
向 OpenSpec 传递提问和文档生成要求时，都必须明确指定 Comet 配置的产物语言，使用 en、zh-CN 这类规范化 ID。change 尚未初始化时，依次读取项目 .comet/config.yaml 和全局 ~/.comet/config.yaml 的 classic.language；初始化后，复用当前有效响应中的 configuration.language；缺少时才使用 comet state get <name> language 读取。没有配置语言时，才采用当前用户请求的语言。生成的 proposal.md、design.md、tasks.md 必须以该语言为主。
0a. 当前 change 绑定
响应已有 agent.continuation.mode 时，先按 comet-classic/reference/auto-transition.md 处理；wait 按 auto-transition.md 区分手动衔接和原任务等待，不能因兼容字段 nextAction.kind: reconcile 再做恢复查询。使用当前响应的命令与输入；Skill 工作实际完成后才使用 completion 提交。下文依据 nextAction.kind 的恢复规则仅用于没有 mode 的旧响应。
恢复已有 change 时，复用同一工作区和 Run 的最新有效 continuation 与归属；冷恢复、外部状态变化或信息缺失时才运行 comet state next <name> --json，再按 data.runtimeFormat 处理：
sdk：复用现有 Run，按data.nextAction.kind恢复；已领取但结果未明的 Action 先核对原结果，不重新创建 change 或重发外部工作。compat：复用原流程和.comet.yaml；不能自动把该 change 改建为 SDK Run。- 命令失败：核对错误、归属记录、Run 和实际状态文件。归属冲突或状态格式异常时停止并报告；若本地 Run 记录丢失，先检查状态文件中的
run_checkpoint，按/comet-classic的恢复步骤沿用已保存阶段。旧状态没有检查点且用户明确同意重启时，才回到 Open 重新核对证据和确认。只有证实尚无任何 Runtime 归属、change 目录有效时，才按所选隔离方式准备工作区并初始化。不得因缺少某一个文件名就重新初始化。
SDK 与旧 change 在冷恢复、工作区变化或绑定信息缺失时，通过以下命令核对并绑定工作区；已有有效选择和 projectRoot 时直接复用：
comet classic workspace resolve <change-name> --json
# 进入返回的 projectRoot
comet state select <change-name>
创建新 change 时，在创建 OpenSpec 基础目录后立即初始化 SDK Run，再运行上述 select 命令；初始化前不得手工写入 change 选择记录。
0b. Open 前工作区决策与准备
创建 Classic change 时，读取 comet-classic/reference/workspace.md。必须先确定工作区，再创建 OpenSpec 产物和 SDK Run，不能推迟到 Build：
- 用户明确要求并行工作时，直接使用
worktree；先准备好独立工作区，再创建 OpenSpec 产物和 state - 用户未指定隔离方式时，按参考文档处理：需要用户选择时，展示可用的
current、branch、worktree选项，推荐理由不能代替用户选择 - 用户选择
current或branch时，仍应串行工作，不得将其描述为适合多个会话同时使用
What ships with it
2 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.
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.
- 3d ago Changed · -38 lines 8d7cf9a2378b
- 22d ago Changed · -2 lines b85fdd2959c6
- 1mo ago Changed · +1 lines 49253439bf55
- 1mo ago Changed · +13 lines · +1 tokens per session d1d3fc158ba4
- 1mo ago First seen · 290 lines · 32 tokens per session scan A 7dbbbe5446cf
comet-open is a skill published in the GitHub repository rpamis/comet (3,232 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 5,714 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 2026-08-30.
Other skills, from other repositories
push-ci
Push to remote and monitor CI. Validates branch safety, executes git push WITH explicit user approval, then monitors CI run status via gh CLI. Use when: user says 'push', 'push and watch CI', 'ship it', 'push-ci'. Not for: committing (use /smart-commit), creating PRs (use /create-pr), merging (use /merge-prep).
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.…
gh-stack
Native stacked pull requests through the github/gh-stack extension. Detects the extension, installs it only after the user approves, resolves the branch chain, and executes gh stack link / gh stack push / gh stack submit --auto under a per-use AskUserQuestion gate. Use when: opening or refreshing a native stack of…
smart-rebase
Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (the developer runs it — no skill executes…
remind
A correction helper that checks which project rules or required steps were missed and loads the relevant guidance.
adr
Write an Architecture Decision Record (ADR) for a feature — Context / Decision / Status / Consequences / Alternatives, filed as docs/features/ /adr- - .md with a 3-digit zero-padded number. Handles the Superseded case: bidirectional linking when a new ADR replaces an old one. Use when: recording why an architectural…