plan

plan is a skill for Claude Code, Codex from ohong/agent-skills. It costs 38 tokens per session (1,270 once invoked), scanned A, original, MIT.

An interactive planning process for software work. It researches the codebase, asks clarifying questions, breaks the work into milestones, and saves an approved plan.

In plain words
What is it for?
Use it to scope a coding task, identify requirements and risks, and create a milestone-based mission plan.
Why use it?
It turns a vague request into agreed steps with clear completion checks before implementation begins.

Skill for Claude CodeCodex

Part of the mission plugin — 6 skills shipped together

Install

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.

agentmods
npx agentmods add skills/ohong/agent-skills/plan
Any agent
npx skills add ohong/agent-skills --skill plan
Clone the repo
git clone --depth 1 https://github.com/ohong/agent-skills

Made for: Claude Code, Codex.

Or install mission, the plugin that ships this one along with the rest of its 6 skills.

Wrote 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.

agentmods badge for plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/ohong/agent-skills/plan.svg)](https://agentmods.dev/skills/ohong/agent-skills/plan)
Your own site
<a href="https://agentmods.dev/skills/ohong/agent-skills/plan"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,270 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.01270
Opus 5 $0.00019 $0.00635
Sonnet 5 $0.00008 $0.00254
Haiku 4.5 $0.00004 $0.00127

Measured 5d ago against content hash 7093ce292864, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

plan scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Vague acceptance criteria.** "The API works" is not verification. "`curl localhost:3000/api/users` returns 200 with a JSON array" is. Without concrete criteria, you can't test your hypotheses.
mission/skills/plan/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mission Planning — The Orientation Phase

"Orientation is the Schwerpunkt. It shapes the way we interact with the environment — hence orientation shapes the way we observe, the way we decide, the way we act." — John Boyd

You are entering the Orientation phase — the most important phase of a mission. Boyd found that the quality of orientation determines everything downstream. A fighter pilot who understands the situation writes the outcome before the fight begins. An agent who understands the codebase writes correct code on the first attempt.

Do not rush this phase. Time spent orienting is the highest-leverage investment in the entire mission.

Task: $ARGUMENTS


Step 1: Observe — Gather raw information

If $ARGUMENTS is empty or vague, ask: "What would you like me to build? Describe the end state."

If a .mission/plan.md already exists, read it and ask: "An existing mission plan was found. Do you want to (a) replace it with a new plan, or (b) refine the existing plan?"

Step 2: Orient — Probe for the full picture

Before planning, build your orientation. Ask 3-7 focused questions covering:

  • Scope boundaries: What's explicitly OUT of scope?
  • Existing code: Are there patterns, conventions, or architecture I should follow?
  • Verification: How will we know each piece works? (existing tests, manual check, specific commands?)
  • Dependencies: Are there external services, APIs, or packages involved?
  • Priority: If this runs long, what's the MVP vs. nice-to-have?

Do NOT proceed until the user answers. Do NOT guess at constraints. Your orientation is only as good as the information you build it from.

Step 3: Orient deeper — Research the codebase

Boyd's orientation has five inputs. Map them:

  1. Project conventions (cultural traditions) — Read CLAUDE.md, README.md, package.json / pyproject.toml. What are the team's norms?
  2. Existing architecture (previous experience) — Map the relevant codebase with focused reads. Use subagents only when the user requests them or the work has genuinely independent, parallel branches.
  3. New information — What did the user tell you? What did you discover that wasn't obvious?
  4. Build/test/lint commands — Identify the verification tools. These are how reality will talk to you.
  5. Analysis & synthesis — Does the task fit cleanly into the existing architecture, or does something need to change? If there's tension, name it now.

Read the full file on GitHub · 107 lines

Changes

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.

  1. 5d ago First seen · 107 lines · 38 tokens per session scan A 7093ce292864

Subscribe to this mod's changes

plan is a skill published in the GitHub repository ohong/agent-skills (3 stars, last pushed 5d ago), licensed MIT. It adds 38 tokens to every session and 1,270 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens