validate_plan

validate_plan is a command for Claude Code from spideynolove/claude-dotfiles. It costs 15 tokens per session (474 once invoked), scanned A, original, MIT.

A command that checks whether an implementation followed a written plan. It runs the plan's automated checks and reports completed, incomplete, failed, or manually reviewable items.

In plain words
What is it for?
Use it after planned development work to inspect commits and changed files, run tests or other listed checks, and produce a validation report.
Why use it?
It gives reviewers evidence about what changed and which success criteria passed, instead of relying only on a progress checklist.

Command for Claude Code

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 commands/spideynolove/claude-dotfiles/validate_plan
Clone the repo
git clone --depth 1 https://github.com/spideynolove/claude-dotfiles

Made for: Claude Code.

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/commands/spideynolove/claude-dotfiles/validate_plan.svg)](https://agentmods.dev/commands/spideynolove/claude-dotfiles/validate_plan)
Your own site
<a href="https://agentmods.dev/commands/spideynolove/claude-dotfiles/validate_plan"><img src="https://agentmods.dev/badge/commands/spideynolove/claude-dotfiles/validate_plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 474 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00015 $0.00474
Opus 5 $0.00008 $0.00237
Sonnet 5 $0.00003 $0.00095
Haiku 4.5 $0.00002 $0.00047

Measured 5d ago against content hash a108246408cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 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.

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.

.claude-global-backup/commands/validate_plan.md · 82 lines

What it actually says

Validate Plan

You are tasked with validating that an implementation plan was correctly executed. Run all automated success criteria, identify deviations, and list what still needs manual verification.

Setup

When invoked:

  1. Locate the plan (use path if provided; otherwise check recent commits or ask)
  2. Gather implementation evidence:
    git log --oneline -n 20
    git diff HEAD~N..HEAD  # cover implementation commits
    
  3. Read the plan completely

Validation Process

Step 1: Discover What Was Done

Spawn parallel research agents to verify:

  • Which files were changed vs what the plan specified
  • Whether tests were added/updated as specified
  • Whether automated criteria commands actually pass

Step 2: Systematic Check Per Phase

For each phase:

  1. Check completion status — look for - [x] checkmarks
  2. Run every command from "Automated Verification"
  3. Document pass/fail
  4. Think about edge cases: error handling, regressions, missing validations

Step 3: Generate Validation Report

## Validation Report: [Plan Name]

### Implementation Status
✓ Phase 1: [Name] — Fully implemented
✓ Phase 2: [Name] — Fully implemented
⚠️ Phase 3: [Name] — Partially implemented

### Automated Verification Results
✓ [command] — passed
✗ [command] — failed: [reason]

### Code Review Findings

#### Matches Plan:
- [Finding: file:line]

#### Deviations from Plan:
- [Deviation: file:line] ([improvement or concern])

#### Potential Issues:
- [Risk or missing piece]

### Manual Testing Required:
- [ ] [Step the human must verify]
- [ ] [Another step]

### Recommendations:
- [Action before merge]

Guidelines

  • Run ALL automated checks — don't skip
  • Be honest about shortcuts or incomplete items from this session
  • Think critically: does the implementation actually solve the problem?
  • Consider maintainability, not just correctness
/create_plan → /implement_plan → /validate_plan → commit → PR
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 · 82 lines · 15 tokens per session scan A a108246408cd

Subscribe to this mod's changes

validate_plan is a command published in the GitHub repository spideynolove/claude-dotfiles (2 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 474 once invoked, about $0.0001 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.