implement_plan

A command for carrying out an approved technical plan stored in thoughts/plans/. It reads the plan and related files, implements its phases, tracks completed work, and adapts when the code differs from the plan.

In plain words
What is it for?
Use it when you already have an approved plan and need its specified changes implemented and marked as complete.
Why use it?
It turns a written implementation plan into tracked code changes while checking that the plan still matches the repository.

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/implement_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 659 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 $0.00659
Opus 5 $0.00000 $0.00329
Sonnet 5 $0.00000 $0.00132
Haiku 4.5 $0.00000 $0.00066

Measured 2d ago against content hash df2c77e20bed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement_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 2d 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/implement_plan.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement Plan

You are tasked with implementing an approved technical plan from thoughts/plans/. These plans contain phases with specific changes and success criteria.

Directory Structure:

  • thoughts/tickets/ - Original feature requests and task descriptions
  • thoughts/plans/ - Implementation plans (the files you'll be executing)
  • thoughts/research/ - Supporting research and investigation notes

Getting Started

When given a plan path:

  • Read the plan completely and check for any existing checkmarks (- [x])
  • Read the original ticket and all files mentioned in the plan
  • Read files fully - never use limit/offset parameters
  • Create a todo list to track your progress
  • Start implementing if you understand what needs to be done

If no plan path provided, ask for one.

Implementation Philosophy

Plans are carefully designed, but reality can be messy. Your job is to:

  • Follow the plan's intent while adapting to what you find
  • Implement each phase fully before moving to the next
  • Verify your work makes sense in the broader codebase context
  • Update checkboxes in the plan as you complete sections

If you encounter a mismatch:

  • STOP and present the issue clearly:
    Issue in Phase [N]:
    Expected: [what the plan says]
    Found: [actual situation]
    Why this matters: [explanation]
    
    How should I proceed?
    

Verification Approach

After implementing a phase:

1. Run Success Criteria Checks

Use technology-appropriate commands:

Node.js/JavaScript: npm test, npm run lint, npm run build Python: pytest, black --check ., mypy . Go: go test ./..., golangci-lint run, go build Rust: cargo test, cargo clippy, cargo build Make-based: make test, make lint, make build

2. Fix Issues and Update Progress

  • Address any failures before moving to the next phase
  • Update checkboxes in the plan file using the Edit tool
  • Update your TodoWrite list

If You Get Stuck

  1. Investigate First - Read all relevant code completely
  2. Use Sub-tasks for targeted help:
    • codebase-locator: Find specific files
    • codebase-analyzer: Understand how code works
    • codebase-pattern-finder: Find similar implementations
  3. Present Issues Clearly - Don't guess, ask for clarification

Read the full file on GitHub · 83 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. 2d ago First seen · 83 lines · 0 tokens per session scan A df2c77e20bed

Subscribe to this mod's changes

implement_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 659 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.