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-nativenpx skills add rpamis/comet --skill comet-nativegit clone --depth 1 https://github.com/rpamis/cometWhat 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 | $0.00034 | $0.05944 |
| Opus 5 | $0.00017 | $0.02972 |
| Sonnet 5 | $0.00007 | $0.01189 |
| Haiku 4.5 | $0.00003 | $0.00594 |
Grade A, and why
comet-native 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 today.
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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comet Native
Native 把需求、完整目标规格、当前进度和验收结论保存在项目中。每完成一个阶段都回到 Runtime 读取下一步，当前只处理 Runtime 指定的阶段。CLI 文本先给出面向用户的 summary 和唯一 NEXT:；需要稳定解析时使用 --json 读取新增的 summary/next/user_message Envelope，只有排查机器状态才使用 --verbose，并在等待用户决定前先转述 userCommunication。
硬性边界
- 磁盘中的
.comet/config.yaml、当前 change、comet-state.yaml和正式产物是工作依据，聊天记忆只作辅助。 - Runtime 管理工作流状态、本机执行状态、日志、锁和事务；所有阶段推进都通过 PATH 中公开的
comet native命令完成，用户不手工执行这些命令。 - 命令不可用时报告 Comet 安装不完整并停止。参数和输出以
comet native <command> --help为准。 - Builder 提交候选，由新的只读 Verifier 作出验收判断；Verifier 的启动方式服从用户选择的推进方式和 Runtime 返回的
continuation。 - Native 主流程由本 Skill 和 Runtime 完成，不依赖任何外部 Skill。
开始或恢复
- 已知 change 名称时，先运行紧凑查询
comet native status <change-name> --json；名称未知时才运行comet native status --json，确定目标后再查询该 change。 - 只有当前动作需要验收文字、Builder 交接、历史或验证详情时才加
--details，并按返回的nextPageArgs逐页读取；只读取覆盖当前scopeIds的页面，不在同一步重复读取完整状态。需要编辑或核对正式正文时才运行show或读取对应 brief/Spec。 - active change 已存在时，进入返回的
workspace.projectRoot并select。Runtime 会扫描已登记的worktree，优先返回绑定分支匹配的工作区；只有多个同样匹配的候选才让用户选择。 - 没有对应 active change 时才创建，并使用配置指定的产物目录。
comet init会按所选 Skill 语言初始化native.language；之后产物跟随项目配置，只有用户明确要求覆盖时才传入--language。
记忆接入
进入 change 工作区并读取 Runtime 当前 phase 后，Agent 自动运行一次：
comet task <project-root> --task "<用户原始请求>" --phase "<phase>" --session "<本次任务稳定标识>" --json
- 只把返回 JSON 的
text加入当前上下文。manifest（注入文本中的<context_manifest>）是 Context Manifest，只包含摘要、应用原因和稳定 ID；当前任务需要正文、来源或验证方式时，运行comet task <project-root> --task "<用户原始请求>" --phase "<phase>" --session "<同一标识>" --expand-context "<id>" --json。路径、操作或阶段变化时，以同一--session和新的--path、--operation、--phase重新选择；未变化内容不会重复投递。 - 若
<active_policies>中包含<verification command="...">，把这些命令加入当前 Verify 的实际检查，并记录真实结果；只有成功执行过的命令才能让对应策略进入强制执行状态。 - 只有用户明确要求长期记住偏好或项目约定时，才调用
comet memory remember <project-root> --text "<偏好或约定>" --scope global|project --json并立即作为显式记忆生效；没有明确长期要求但出现可跨任务复用的稳定协作方式时，才调用comet memory observe <project-root> --text "<协作方式>" --workflow <workflow> --change <change-id> --candidate-key <stable-topic-key> --json。两者都不得写任务摘要、实现进展、命令输出或测试结果。 - 实际采用某条上下文后，从 JSON 的
applications[].applicationId（Hook 文本中的application_id）取得标识，并在结果明确时运行comet task <project-root> --task "<用户原始请求>" --application "<application-id>" --outcome used-successfully|ignored|overridden|corrected|contributed-to-failure --json；不得为未实际使用的条目回写成功。验证、编译或 linter 失败时直接按诊断修复并重跑。任务结束仍调用comet task <project-root> --task "<用户原始请求>" --complete --workflow <workflow> --change <change-id> --json记录工作流检查点。命令不可用、没有内容或自动检索失败时继续工作；无 Hook 平台由本 Skill 使用以上同一接口，comet memory context只作为兼容入口。
What ships with it
6 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.
- today Changed · +5 lines 6c81b5cea300
- 3d ago First seen · 109 lines · 34 tokens per session scan A 8ec2817ca409
comet-native is a skill published in the GitHub repository rpamis/comet (2,902 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 5,944 once invoked, about $0.0002 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-wiki
Use when initializing, checking, enriching, or reviewing agent-spec code live wiki pages, sourcefiles trace, or Rust architecture inventory.
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.