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 commands/ishandutta2007/awesome-agent-skills/plangit clone --depth 1 https://github.com/ishandutta2007/Awesome-Agent-SkillsWhat 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 | $0.00013 | $0.00132 |
| Opus 5 | $0.00006 | $0.00066 |
| Sonnet 5 | $0.00003 | $0.00026 |
| Haiku 4.5 | $0.00001 | $0.00013 |
Grade A, and why
plan 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 yesterday.
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
88% identical to plan — 2 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.
What it actually says
Invoke the agent-skills:planning-and-task-breakdown skill.
Read the existing spec (SPEC.md or equivalent) and the relevant codebase sections. Then:
- Enter plan mode — read only, no code changes
- Identify the dependency graph between components
- Slice work vertically (one complete path per task, not horizontal layers)
- Write tasks with acceptance criteria and verification steps
- Add checkpoints between phases
- Present the plan for human review
Save the plan to tasks/plan.md and task list to tasks/todo.md.
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.
- yesterday First seen · 17 lines · 13 tokens per session scan A 4a14758a4596
plan is a command published in the GitHub repository ishandutta2007/Awesome-Agent-Skills (20 stars, last pushed 22d ago), licensed MIT. It adds 13 tokens to every session and 132 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to plan, differing in 2 lines, and is treated as a copy.
Other commands, from other repositories
screen-usecase
筛选、验证并撰写 OpenClaw 用例。输入来源 URL 或描述，输出适配评估或完整用例 PR。.
code-review
Code review — local uncommitted changes or GitHub PR (pass PR number/URL for PR mode).
docs-fe
Generate a concise FE handoff doc for changed endpoints — branch, APIs, request/response contracts, search params, error codes.
coding-level
Set Claude's coding explanation level for this session/project (-1=Default → 5=God Mode).
brainstorm
Explore and debate solutions before writing code — scout codebase, ask clarifying questions, research options, and produce a structured decision report. Ends with → /ck:plan (implement) or /ck:journal (archive). No code is written.
cook
Implement a plan phase by phase. Cook never writes or runs tests; every phase requires an APPROVED ck:quality gate before completion. Modes: --fast or --hard. Flag: --tdd. --json selects the phased master plan.json; --plan selects a Markdown plan.md.