Borrowing it
Nothing to install: this file belongs to akiojin/llmlb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/akiojin/llmlb/develop/.codex/skills/.system/plan/SKILL.mdgit clone --depth 1 https://github.com/akiojin/llmlbWrote 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/akiojin/llmlb/plan)<a href="https://agentmods.dev/skills/akiojin/llmlb/plan"><img src="https://agentmods.dev/badge/skills/akiojin/llmlb/plan/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/akiojin/llmlb/plan"><img src="https://agentmods.dev/badge/skills/akiojin/llmlb/plan.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00058 | $0.01473 |
| Opus 5.5 | $0.00023 | $0.00589 |
| Sonnet 5.5 | $0.00012 | $0.00295 |
| Haiku 4.5 | $0.00006 | $0.00147 |
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 8d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan
Overview
Draft structured plans that clarify intent, scope, requirements, action items, testing/validation, and risks.
Optionally, save plans to disk as markdown files with YAML frontmatter and free-form content. When drafting in chat, output only the plan body without frontmatter; add frontmatter only when saving to disk. Only write to the plans folder; do not modify the repository codebase.
This skill can also be used to draft codebase or system overviews.
Core rules
- Resolve the plans directory as
$CODEX_HOME/plansor~/.codex/planswhenCODEX_HOMEis not set. - Create the plans directory if it does not exist.
- Never write to the repo; only read files to understand context.
- Require frontmatter with only
nameanddescription(single-line values) for on-disk plans. - When presenting a draft plan in chat, omit frontmatter and start at
# Plan. - Enforce naming rules: short, lower-case, hyphen-delimited; filename must equal
<name>.md. - If a plan is not found, state it clearly and offer to create one.
- Allow overview-style plans that document flows, architecture, or context without a work checklist.
Decide the task
- Find/list: discover plans by frontmatter summary; confirm if multiple matches exist.
- Read/use: validate frontmatter; present summary and full contents.
- Create: inspect repo read-only; choose plan style (implementation vs overview); draft plan; write to plans directory only.
- Update: load plan; revise content and/or description; preserve frontmatter keys; overwrite the plan file.
- Delete: confirm intent, then remove the plan file if asked.
Plan discovery
- Prefer
scripts/list_plans.pyfor quick summaries. - Use
scripts/read_plan_frontmatter.pyto validate a specific plan. - If name mismatches filename or frontmatter is missing fields, call it out and ask whether to fix.
Plan creation workflow
- Scan context quickly: read README.md and obvious docs (docs/, CONTRIBUTING.md, ARCHITECTURE.md); skim likely touched files; identify constraints (language, frameworks, CI/test commands, deployment).
- Ask follow-ups only if blocked: at most 1-2 questions, prefer multiple-choice. If unsure but not blocked, state assumptions and proceed.
- Identify scope, constraints, and data model/API implications (or capture existing behavior for an overview).
- Draft either an ordered implementation plan or a structured overview plan with diagrams/notes as needed.
- Immediately output the plan body only (no frontmatter), then ask the user if they want to 1. Make changes, 2. Implement it, 3. Save it as per plan.
- If the user wants to save it, prepend frontmatter and save the plan under the computed plans directory using
scripts/create_plan.py.
What ships with it
5 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.
- 8d ago First seen · 181 lines · 58 tokens per session scan A 7144a4dfbe56
plan is a skill published in the GitHub repository akiojin/llmlb (10 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 1,473 once invoked, about $0.0002 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 2026-10-21.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…