plan-and-apply

plan-and-apply is a skill for Claude Code, Codex from wangbin3162/agents-skills. It costs 107 tokens per session (1,472 once invoked), scanned A, original, MIT.

A guided workflow for analysing a non-trivial coding task, planning it in small steps, applying the changes, and checking the result.

In plain words
What is it for?
Planning multi-file changes, refactors, migrations, and other tasks that need staged implementation, progress tracking, and verification.
Why use it?
It reduces scope drift, premature edits, oversized rewrites, and unsupported claims that a change is complete.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Planning multi-file changes, refactors, migrations, and other tasks that need staged implementation, progress tracking, and verification.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wangbin3162/agents-skills/plan-and-apply
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.

Any agent
npx skills add wangbin3162/agents-skills --skill plan-and-apply
Clone the repo
git clone --depth 1 https://github.com/wangbin3162/agents-skills

Made for: Claude Code, Codex.

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-and-apply

README.md
[![agentmods](https://agentmods.dev/badge/skills/wangbin3162/agents-skills/plan-and-apply/github.svg)](https://agentmods.dev/skills/wangbin3162/agents-skills/plan-and-apply)
Your own site
<a href="https://agentmods.dev/skills/wangbin3162/agents-skills/plan-and-apply"><img src="https://agentmods.dev/badge/skills/wangbin3162/agents-skills/plan-and-apply/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.

agentmods 80×15 button for plan-and-apply

Your own site · 80×15
<a href="https://agentmods.dev/skills/wangbin3162/agents-skills/plan-and-apply"><img src="https://agentmods.dev/badge/skills/wangbin3162/agents-skills/plan-and-apply.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,472 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00107 $0.01472
Opus 5 $0.00053 $0.00736
Sonnet 5 $0.00021 $0.00294
Haiku 4.5 $0.00011 $0.00147

Measured 9d ago against content hash 37d684dfae23, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

plan-and-apply 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 9d 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.

skills/plan-and-apply/SKILL.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan And Apply

This skill is an upper-layer execution workflow for non-trivial development tasks.

It exists to stop four common failures:

  • changing code before understanding the task
  • drifting outside the requested scope
  • doing large rewrites when a local fix is enough
  • claiming completion without verification

Use it to control execution rhythm. Do not use it for simple one-step questions or tiny edits that do not need planning.

When to use

Use this skill when any of these are true:

  • the user says 先分析先规划不要直接改
  • the task spans multiple files or modules
  • the task is a migration, refactor, or structured feature implementation
  • the task needs a clear task list, progress tracking, or staged rollout
  • the user cares about strict boundaries, minimal change, or explicit regression checks

Do not use this skill when:

  • the user only wants explanation or brainstorming
  • the change is trivial, isolated, and low risk
  • the task is pure review with no implementation

Core promise

Follow this order unless the user explicitly asks for a narrower path:

  1. Read rules first
  2. Clarify task scope and constraints
  3. Decide whether planning is required
  4. Break work into the smallest viable slices
  5. Apply only the current slice
  6. Verify the change and do regression checks
  7. Close out with result, validation, and remaining risk

Step 1: Read rules first

Before implementation, read the project-level instructions that control behavior.

Priority order:

  1. lessons.md
  2. AGENTS.md
  3. task-specific rule files mentioned by the user
  4. relevant reference implementation or old version

If there is no lessons.md, continue without blocking. Do not invent one.

Step 2: Clarify the task

Before changing anything, answer these questions from local context:

  1. What is the actual requirement?
  2. What constraints did the user set?
  3. What are the main risks?
  4. What is the simplest viable approach?
  5. How will the result be verified?

If a key constraint is missing and guessing would be risky, ask a short direct question. Otherwise, proceed with the safest reasonable assumption.

Read the full file on GitHub · 226 lines

Files

What ships with it

2 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.

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. 9d ago First seen · 226 lines · 107 tokens per session scan A 37d684dfae23

Subscribe to this mod's changes

plan-and-apply is a skill published in the GitHub repository wangbin3162/agents-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 1,472 once invoked, about $0.0005 per session on Opus 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 2026-08-31.

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

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…

vercel/next.js · 83 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