validate_plan

validate_plan is a command for coding agents from adrielp/ai-engineering-harness. It costs 0 tokens per session (516 once invoked), scanned A, original, Apache-2.0.

A command for checking whether an implementation plan was carried out correctly and whether its success criteria were met.

In plain words
What is it for?
Use it to read a plan, inspect code and git history, run verification commands, consider edge cases, and produce a validation report.
Why use it?
It helps find incomplete work, unexpected changes, missing tests, and other differences between the plan and the finished implementation.

Command

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/adrielp/ai-engineering-harness/validate_plan
Clone the repo
git clone --depth 1 https://github.com/adrielp/ai-engineering-harness
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 516 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 $0.00000 $0.00516
Opus 5 $0.00000 $0.00258
Sonnet 5 $0.00000 $0.00103
Haiku 4.5 $0.00000 $0.00052

Measured 3d ago against content hash 4c5636a84648, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

opencode/commands/validate_plan.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validate Plan

You are tasked with validating that an implementation plan was correctly executed, verifying all success criteria and identifying any deviations or issues.

Initial Setup

When invoked:

  1. Determine context - Are you in an existing conversation or starting fresh?
  2. Locate the plan - Use provided path or search thoughts/plans/
  3. Gather implementation evidence via git history

Validation Process

Step 1: Context Discovery

  1. Read the implementation plan completely
  2. Identify what should have changed
  3. Spawn parallel research tasks using:
    • codebase-analyzer: Verify implementation details
    • codebase-locator: Find modified files
    • explore: Check test coverage

Step 2: Systematic Validation

For each phase:

  1. Check completion status - Look for checkmarks
  2. Run automated verification - Execute success criteria commands
  3. Assess manual criteria - List what needs manual testing
  4. Think about edge cases

Step 3: Generate Validation Report

## Validation Report: [Plan Name]

### Implementation Status
- Phase 1: [Name] - Fully implemented
- Phase 2: [Name] - Partially implemented (see issues)

### Automated Verification Results
- Build passes: `npm run build`
- Tests pass: `npm test`
- Linting issues: `npm run lint` (X warnings)

### Code Review Findings

#### Matches Plan:
- [What was implemented correctly]

#### Deviations from Plan:
- [What differs from plan]

#### Potential Issues:
- [Concerns discovered]

### Manual Testing Required:
1. [ ] Verify [feature] works
2. [ ] Test error states

### Recommendations:
- [Actionable next steps]

Relationship to Other Commands

Recommended workflow:

  1. /create_plan - Create implementation plan
  2. /implement_plan - Execute the implementation
  3. /commit - Create atomic commits
  4. /validate_plan - Verify implementation correctness
  5. Create PR

Key Principles

  1. Understand Before Validating - Read the entire plan first
  2. Be Objective and Critical - Validate functionality, not just presence
  3. Verify Comprehensively - Run all automated checks
  4. Communicate Clearly - Provide specific file references
  5. Think Long-term - Consider maintainability

Read the full file on GitHub · 80 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. 3d ago First seen · 80 lines · 0 tokens per session scan A 4c5636a84648

Subscribe to this mod's changes

validate_plan is a command published in the GitHub repository adrielp/ai-engineering-harness (20 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 516 tokens. 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.