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/openspec-onboardnpx skills add rpamis/comet --skill openspec-onboardgit 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/openspec-onboard)<a href="https://agentmods.dev/skills/rpamis/comet/openspec-onboard"><img src="https://agentmods.dev/badge/skills/rpamis/comet/openspec-onboard.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 | $0.00026 | $0.03360 |
| Opus 5 | $0.00013 | $0.01680 |
| Sonnet 5 | $0.00005 | $0.00672 |
| Haiku 4.5 | $0.00003 | $0.00336 |
Grade A, and why
openspec-onboard 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.
This is a copy
73% identical to openspec-onboard — 100 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 555 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guide the user through their first complete OpenSpec workflow cycle. This is a teaching experience—you'll do real work in their codebase while explaining each step.
Preflight
Before starting, check if the OpenSpec CLI is installed:
# Unix/macOS
openspec --version 2>&1 || echo "CLI_NOT_INSTALLED"
# Windows (PowerShell)
# if (Get-Command openspec -ErrorAction SilentlyContinue) { openspec --version } else { echo "CLI_NOT_INSTALLED" }
If CLI not installed:
OpenSpec CLI is not installed. Install it first, then come back to
/opsx:onboard.
Stop here if not installed.
Phase 1: Welcome
Display:
## Welcome to OpenSpec!
I'll walk you through a complete change cycle—from idea to implementation—using a real task in your codebase. Along the way, you'll learn the workflow by doing it.
**What we'll do:**
1. Pick a small, real task in your codebase
2. Explore the problem briefly
3. Create a change (the container for our work)
4. Build the artifacts: proposal → specs → design → tasks
5. Implement the tasks
6. Archive the completed change
**Time:** ~15-20 minutes
Let's start by finding something to work on.
Phase 2: Task Selection
Codebase Analysis
Scan the codebase for small improvement opportunities. Look for:
- TODO/FIXME comments - Search for
TODO,FIXME,HACK,XXXin code files - Missing error handling -
catchblocks that swallow errors, risky operations without try-catch - Functions without tests - Cross-reference
src/with test directories - Type issues -
anytypes in TypeScript files (: any,as any) - Debug artifacts -
console.log,console.debug,debuggerstatements in non-debug code - Missing validation - User input handlers without validation
Also check recent git activity:
# Unix/macOS
git log --oneline -10 2>/dev/null || echo "No git history"
# Windows (PowerShell)
# git log --oneline -10 2>$null; if ($LASTEXITCODE -ne 0) { echo "No git history" }
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 · 555 lines · 26 tokens per session scan A d3f8c1933b70
openspec-onboard is a skill published in the GitHub repository rpamis/comet (2,927 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 3,360 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 73% identical to openspec-onboard, differing in 100 lines, and is treated as a copy.
Other skills, from other repositories
fp-brief
First-principles briefing from technical documents. Use when: understanding why decisions were made, onboarding to feature reasoning, reviewing decision chains, explaining doc from first principles. Not for: PM/CTO summary (use project-brief), pre-doc analysis (use feasibility-study), code explanation (use…
codex-explain
Explain complex code via Codex exec. Use when: understanding complex logic, tracing data flow, onboarding to unfamiliar code. Not for: code review (use codex-code-review), exploration (use code-explore). Output: structured explanation at chosen depth.
sharingan
Replicate knowledge from any source as sd0x-dev-flow skill definition. Use when: copying skills from repos, adapting patterns from articles/papers/code, converting knowledge to skill format. Not for: research without skill output (use deep-research), creating skills from scratch (use skill-creator), project onboarding…
dojo-teach
Codojo S3 阶段唯一 skill:正式交互式教学。按 .codojo/task.md 学习计划逐个知识点进行教学,每个知识点分理论 + 实践两环节。 两种状态模式(自动路由): start : schedule.md 进度 = 0% 或刚从 S2 进来 → 从第一个知识点开始 resume : schedule.md 进度 > 0% 且 < 100% → 定位到上次断点继续 确认驱动:理论环节等用户回复"理解"才进实践,实践环节等用户回复"完成" 才推进下一知识点。全程实时更新 schedule.md 记录进度百分比。 触发关键词:开始学习、继续学习、S3、教我、teach、下一个知识点、…
dojo-hack
Codojo S4 阶段唯一 skill:魔改(可选进阶)。S3 教学完成后的实战环节, AI 基于项目分析为用户推荐多个魔改方向(加功能、重构、性能优化等), 用户可多选或自定义,然后制定 .codojo/plan.md 并按计划对项目进行实际改造。 两种状态模式(自动路由): init : plan.md 不存在 → 推荐魔改方向 → 用户选择 → 生成 plan.md resume : plan.md 已存在 → 读取计划 → 从上次断点继续执行 plan.md 随用户需求持续更新,S4 不设边界,直到用户主动说"结束"为止。 触发关键词:魔改、改造项目、加功能、S4、hack、我想改这个项目、…
dojo-plan
Codojo S2 阶段唯一 skill:学习计划生成。从 S1 产出的 .codojo/open-questions.md 读取用户能力画像,结合项目结构分析, 生成个性化学习计划 task.md + 进度跟踪表 schedule.md。 已掌握的内容跳过或简化,重点放在用户薄弱环节。 状态模式: generate : task.md 不存在 → 读取评估结果 + 分析项目 → 生成计划 regenerate : 用户明确要求重新生成计划 → 覆盖已有 task.md + schedule.md 触发关键词:生成学习计划、制定计划、S2、学习路径、plan、规划学习路线、 帮我安排学习顺序、生成 schedule。…