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-github-ci-triagegit 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-github-ci-triage)<a href="https://agentmods.dev/skills/rpamis/comet/comet-github-ci-triage"><img src="https://agentmods.dev/badge/skills/rpamis/comet/comet-github-ci-triage/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-github-ci-triage"><img src="https://agentmods.dev/badge/skills/rpamis/comet/comet-github-ci-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00072 | $0.00530 |
| Opus 5.5 | $0.00029 | $0.00212 |
| Sonnet 5.5 | $0.00014 | $0.00106 |
| Haiku 4.5 | $0.00007 | $0.00053 |
Grade A, and why
comet-github-ci-triage 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 1mo 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.
What it actually says
Comet GitHub CI 分诊
先读取 ../comet-github/references/maintainer-contract.md。默认只做诊断；只有用户要求时才实施修复。
检查准确的远端状态
- 解析 PR，记录当前 head SHA 和目标分支。
- 运行
gh pr checks <pr> --json name,state,bucket,link,workflow,startedAt,completedAt。 - 对失败 job 使用
gh run view <run-id> --log-failed或最小范围的 job 日志检查真实失败边界。不要在没有日志证据时相信聚合助手摘要。 - 检查可合并状态，并确认显示的检查属于当前 head。过期 run 不能证明当前代码有问题。
- Codecov 页面信息不完整时，通过可用 API 检查受影响文件和 patch coverage 元数据，并报告准确 head 和覆盖率范围。
分类失败原因
判断红色结果属于：
- 生产代码；
- 测试 fixture 或冻结契约投影；
- 生成 Runtime 漂移或构建输出不确定；
- 依赖、工具链或平台环境；
- 凭证、权限或 Runner 配置；
- 过期检查或合并冲突；
- 未解决的覆盖率阈值。
用户要求实施时，在本地复现最小决定性边界。Windows 环境需要先区分沙箱、凭证或占位可执行文件噪音与真实 CI 失败，再修改产品代码。
准确报告状态
返回当前 head SHA、失败 job、根因、证据和最小动作。把远端状态与本地检查分开报告。超时、缺失、过期或尚未启动的检查都标记为“未验证”。
在准确最终 head 的新检查成功前，绝不宣称 CI 全绿。如果需要修复，将已确认范围交给 comet-github-issue-fix，获得授权后再使用 comet-safe-delivery。
What ships with it
1 file 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.
- 1mo ago First seen · 38 lines · 72 tokens per session scan A 133dc3c600bf
comet-github-ci-triage is a skill published in the GitHub repository rpamis/comet (3,215 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 530 once invoked, about $0.0003 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
gh-fix-ci
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use gh to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.
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).
issue-analyze
GitHub Issue and PR review thread deep analysis with Codex blind verdict. Use when: analyzing issue root cause, classifying problems, investigation planning, triaging PR review comments for actionability. Not for: fixing bugs (use bug-fix), code exploration (use code-explore). Output: classified analysis + verdict…
debug
Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.
watch-ci
Monitor GitHub Actions CI runs until completion. Use when: watching CI after push, checking build status, monitoring PR checks, waiting for CI completion, user says 'watch CI', 'check CI', 'CI status', 'monitor build', or /watch-ci. Not for: pushing code (use push-ci), creating PRs (use create-pr). Output: per-run…
code-explore
Pure Claude code investigation. Use when: tracing execution paths, understanding architecture, diagnosing issues. Not for: dual-perspective review (use code-investigate), code review (use codex-code-review). Output: analysis report with findings.