validate-plan

validate-plan is a skill for Claude Code, Codex from nikeyes/stepwise-dev. It costs 14 tokens per session (446 once invoked), scanned A, original, Apache-2.0.

A plan-checking guide that compares a completed software implementation with the original plan and its success criteria.

In plain words
What is it for?
Reading plans and referenced files, running the specified checks, comparing each phase with the code, and assessing whether tests prove the intended behavior.
Why use it?
It catches missing work, incorrect claims, deviations, and weak tests that may be hidden by a simple passing test run.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: model in frontmatter.

Part of the stepwise-core plugin — 14 skills, 10 agents shipped together

Good fit Reading plans and referenced files, running the specified checks, comparing each phase with the code, and assessing whether tests prove the intended behavior.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nikeyes/stepwise-dev/validate-plan
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 nikeyes/stepwise-dev --skill validate-plan
Clone the repo
git clone --depth 1 https://github.com/nikeyes/stepwise-dev

Made for: Claude Code, Codex.

Or install stepwise-core, the plugin that ships this one along with the rest of its 14 skills, 10 agents.

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 validate-plan

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

agentmods 80×15 button for validate-plan

Your own site · 80×15
<a href="https://agentmods.dev/skills/nikeyes/stepwise-dev/validate-plan"><img src="https://agentmods.dev/badge/skills/nikeyes/stepwise-dev/validate-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 446 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00014 $0.00446
Opus 5.5 $0.00006 $0.00178
Sonnet 5.5 $0.00003 $0.00089
Haiku 4.5 $0.00001 $0.00045

Measured 8d ago against content hash cb3da8f3ffb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

validate-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.

core/skills/validate-plan/SKILL.md · 52 lines

What it actually says

Validate Plan

Check that the code does what an implementation plan asks.

Input

  • If a plan path is provided, use it
  • Otherwise, search thoughts/shared/plans/ or ask the user

Validation Steps

  1. Read the plan completely: every phase, checkbox, success criterion and manual verification item.

  2. Run the automated verification its success criteria name, and capture the output.

  3. Compare each phase with the code, at the level of behavior. The plan was written before the code met reality; keep the code's solution when it does the job.

    • Does the system do what the phase asks, and is each behavior tested? Does the public contract match: endpoints, request and response shapes, error codes, signatures other code relies on?
    • Do checked items ([x]) match the code?
    • A different internal approach, or tests the plan didn't list, is not a finding. Under "Plan out of date", note only the deviations that would mislead someone reading the plan, such as a different approach, data structure or interface detail. Leave out cosmetic changes and extra tests.
  4. Assess test quality: read the tests, don't just run them. Are assertions missing or trivial? Do they mock the thing they're supposed to test?

  5. Look for regressions in the pre-existing behavior of the modified files.

  6. Flag vague or unmeasurable criteria as unverifiable instead of inventing interpretations.

Report Format

## Validation Report: [Plan Name]

### Implementation Status
Phase N: [Name] — [Fully implemented | Gaps found | NOT implemented]

### Automated Verification
[Commands run, pass/fail]

### Findings
[Missing or broken behavior, contract changes, weak tests, regressions, unverifiable criteria]

### Plan out of date
[What the plan said, what the code does, and why]
Files

What ships with it

1 file 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. 8d ago Changed · -13 lines cb3da8f3ffb9
  2. 1mo ago Changed 21b90567e3dd
  3. 1mo ago Changed 5d4f4ba6edd7
  4. 1mo ago First seen · 65 lines · 14 tokens per session scan A c6cd477d2613

Subscribe to this mod's changes

validate-plan is a skill published in the GitHub repository nikeyes/stepwise-dev (24 stars, last pushed 6d ago), licensed Apache-2.0. It adds 14 tokens to every session and 446 once invoked, about $0.0001 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 2026-08-30.

Related

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…

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

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 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

Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…

vercel/next.js · 123 tokens