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-anynpx skills add rpamis/comet --skill comet-anygit 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-any)<a href="https://agentmods.dev/skills/rpamis/comet/comet-any"><img src="https://agentmods.dev/badge/skills/rpamis/comet/comet-any.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 | $0.01973 |
| Opus 5 | $0.00015 | $0.00986 |
| Sonnet 5 | $0.00006 | $0.00395 |
| Haiku 4.5 | $0.00003 | $0.00197 |
Grade A, and why
comet-any 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 5d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comet Any - Skill Creator
/comet-any 是 Comet 的 Skill 创建向导。用户只需要描述想要的工作流;本 Skill 负责读取真实 Skill、提出方案、等待确认、生成可验证的 Comet-native Skill Bundle,并通过内部 CLI 完成 eval、review、publish readiness 和安装预览。
普通用户第一层只看到三种起点:
基于 /comet-classic 的五阶段定制:覆盖open / design / build / verify / archive五阶段的 Skill 编排,但不修改/comet-classic永久入口本身。创建全新 workflow Skill:从目标和候选 Skills 生成新的workflow-kernel。整理已有 Skill:读取已有 Skill,补齐 Workflow Node、Skill Binding、Output Schema、Guardrail、Handoff、eval 和 readiness。
后端 Bundle、Factory、composition 仍是内部审计词;不要把它们作为普通用户的第一屏概念。
核心模型
所有路径都必须编译到同一种 Workflow Contract:
Workflow Node:流程中的可恢复节点,例如open、design、plan、execute、subagent-execute、review、verify、archive。Node Responsibility:该 Node 在 Agent workflow 中承担的职责,用来解释它为什么存在、需要产出什么、能否替换。Skill Binding:某个 Node 的实现 Skill 或辅助 Skill。Required Skill Call:要求 Node 内必须调用某个 Skill,不替换 Node implementation。例如execute和subagent-execute必须调用elementui,review必须调用whitebox-code-standard。Output Schema:Node 必须产出的文件、状态或 evidence。Output Schema 必须挂到具体 Workflow Node 才算生效;只定义在workflow.outputSchemas里不会触发 guard、eval 或 readiness。脚本、eval、readiness 只依赖挂到 Node 的 Output Schema,不依赖 Skill 名称。Guardrail:阻断或放行 Node 推进的检查。Handoff:子代理或跨 Node 交接时必须带回的 evidence。workflow-protocol.json:生成包的唯一运行事实源,kind 为comet-five-phase-overlay或workflow-kernel。
受保护边界
comet-five-phase-overlay 保留 Comet Classic 五阶段主流程和 .comet.yaml 状态语义。普通模式下:
comet-five-phase-overlay的主状态只来自 Classic layout resolver 绑定的<classic-change-dir>/.comet.yaml;没有 active change 或多个 active changes 时必须阻塞并请用户选择。- 不得创建
.comet/runs/<workflow>/state.json作为 Comet overlay 主状态。Bundle 草稿、eval evidence 和 publish readiness 可以有自己的证据文件,但不能替代.comet.yaml。 controlNode 不允许 override:open、execute、verify、archive。producerNode 可以 override:design、plan,但必须满足对应 Output Schema。handoff和guardrailNode 可以 require / augment。- 用户坚持替换 control Node 时,改走高级
workflow-kernel,并要求重新声明 state、Output Schema 和 Guardrail。 - 所有 Node 都必须用 responsibility 说明职责,不使用内部坐标作为用户理解流程的方式。
What ships with it
12 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 166 B
- reference/authored-zone-example.md 8.2 KB
- reference/authoring-protocol.json 2.8 KB
- reference/authoring-subagents.md 5.1 KB
- reference/bundle-authoring.md 6.3 KB
- reference/eval-provider.md 3.1 KB
- reference/subagents/pause-points-author.md 4.2 KB
- reference/subagents/reference-author.md 3.0 KB
- reference/subagents/script-author.md 3.5 KB
- reference/subagents/skill-core-author.md 6.9 KB
- reference/subagents/skill-reviewer.md 6.4 KB
- reference/subagents/workflow-entry-author.md 6.1 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.
- 5d ago First seen · 120 lines · 29 tokens per session scan A eb9137b3757b
comet-any is a skill published in the GitHub repository rpamis/comet (2,914 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 1,973 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.
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).
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.