implement_plan

implement_plan is a command for Claude Code, OpenCode from allisoneer/agentic_auxilary. It costs 16 tokens per session (1,371 once invoked), scanned A, original, MIT.

A workflow that carries out an approved technical plan in phases, checking each phase before moving to the next.

In plain words
What is it for?
Use it to load a saved plan, track implementation tasks, make the planned changes, run checks, reflect on results, and stop for approval if the codebase differs materially from the plan.
Why use it?
It prevents implementation from silently drifting away from the plan and requires verification instead of treating code changes as finished immediately.

Command for Claude CodeOpenCode

Written for Claude Code and OpenCode: $ARGUMENTS substitution, but also installed under .opencode/. Also seen: agent in frontmatter.

Good fit Use it to load a saved plan, track implementation tasks, make the planned changes, run checks, reflect on results, and stop for approval if the codebase differs materially from the plan.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/allisoneer/agentic_auxilary/implement_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.

Clone the repo
git clone --depth 1 https://github.com/allisoneer/agentic_auxilary

Made for: Claude Code, OpenCode.

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 implement_plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/implement_plan/github.svg)](https://agentmods.dev/commands/allisoneer/agentic_auxilary/implement_plan)
Your own site
<a href="https://agentmods.dev/commands/allisoneer/agentic_auxilary/implement_plan"><img src="https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/implement_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 implement_plan

Your own site · 80×15
<a href="https://agentmods.dev/commands/allisoneer/agentic_auxilary/implement_plan"><img src="https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/implement_plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,371 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 $0.00016 $0.01371
Opus 5.5 $0.00006 $0.00548
Sonnet 5.5 $0.00003 $0.00274
Haiku 4.5 $0.00002 $0.00137

Measured 1mo ago against content hash 4df52c3beaa2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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/command/implement_plan.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<workflow_contract>

  1. Follow all 4 steps in order.
  2. Read the implementation plan fully before doing any code changes.
  3. Use todowrite in Step 1 to create granular implementation and verification todos.
  4. Keep exactly one todo in_progress at a time and mark items complete immediately after finishing them.
  5. Do not skip verification; each phase must be implemented, verified, and reflected on before advancing.
  6. If the codebase materially diverges from plan expectations, stop, document the mismatch, and ask the user before proceeding.
  7. When resuming partial work, trust completed checkmarks and prior artifacts unless current files clearly contradict them. </workflow_contract>

MAKE SURE you follow ALL 4 steps in order. Step 1 loads context and creates your detailed todo list. Steps 2-4 form the implementation loop: implement phase → verify and reflect → iterate.

<step_1>

Step 1: Load Plan Context and Build the Todo List

  1. Parse the implementation plan path from <userMessage>.
  2. If no plan path was provided, ask the user for the implementation plan path and stop.
  3. Read the implementation plan fully. If it does not exist, report that clearly and stop.
  4. If the plan filename ends with _implementation.md, read the sibling {pair_base}_requirements.md. Warn if it is missing, but continue.
  5. Call tools_thoughts_list_documents filtered to artifact documents and look for prior handoff or progress artifacts whose filenames start with plan_{basename}_.
  6. Read any matching artifacts so you understand completed work, past decisions, and resume context.
  7. Read all files explicitly referenced in the implementation plan before editing them.
  8. Parse the plan into granular todos. For each phase, create:
    • one todo per significant implementation change
    • one verification todo for that phase's success criteria
  9. If the plan already contains completed checkmarks or the artifacts show prior completion, reflect that in the initial todo state unless the current code clearly contradicts it.

Good example todos

  • Phase 1: Add rate_limit.rs middleware file — New file with RateLimiter struct and middleware fn
  • Phase 1: Update router.rs to use rate limiter — Import and wrap routes
  • Phase 1: Add RATE_LIMIT_RPS config key — Add to config.rs with default 100
  • Verify Phase 1 — Run cargo test rate_limit, check middleware applies to /api routes
  • Phase 2: Add Redis backend for rate limiting — Add redis client, update RateLimiter

Bad example todos

  • Phase 1
  • Do the implementation
  • Run tests

</step_1>

<step_2>

Read the full file on GitHub · 141 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. 1mo ago First seen · 141 lines · 16 tokens per session scan A 4df52c3beaa2

Subscribe to this mod's changes

implement_plan is a command published in the GitHub repository allisoneer/agentic_auxilary (79 stars, last pushed 6d ago), licensed MIT. It adds 16 tokens to every session and 1,371 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 2026-09-08.