plan

A command for creating, reviewing, revising, or saving an execution plan with goals, acceptance checks, and work steps.

In plain words
What is it for?
Use it to plan coding work, define acceptance criteria, assign each step a capability, and save a valid plan in an OpenArche session or requested document.
Why use it?
It makes the expected result and the conditions for calling a task complete explicit before execution begins.

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/done-0/openarche/plan
Clone the repo
git clone --depth 1 https://github.com/Done-0/openarche
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 295 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 $0.00008 $0.00295
Opus 5 $0.00004 $0.00148
Sonnet 5 $0.00002 $0.00059
Haiku 4.5 $0.00001 $0.00030

Measured 2d ago against content hash 8d7d8c3510fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

commands/plan.md · 43 lines

What it actually says

Use this command to inspect, draft, revise, or save a real execution plan.

Required behavior:

  1. Build a plan with these fields:
    • objective
    • acceptance criteria
    • execution steps
  2. Every execution step must include:
    • title
    • capability
    • outcome
  3. Only use valid capability names:
    • planning
    • worktree
    • browser
    • observability
    • review
    • maintenance
    • knowledge
  4. Keep the plan valid under current product rules:
    • objective must not be empty
    • there must be at least one acceptance criterion
    • there must be at least one execution step
    • duplicate acceptance criteria are not allowed
    • duplicate capability/title step pairs are not allowed
    • step titles and outcomes must not be empty

When presenting the plan, organize it into:

  • objective
  • acceptance criteria
  • execution steps
  • capability coverage

If the user asks to save it inside the live harness session, update .openarche/sessions/<plan-id>/state.json and keep the runbook.plan section valid. If the user explicitly asks for a standalone document outside the live session, write it to the location they requested.

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 · 43 lines · 8 tokens per session scan A 8d7d8c3510fb

Subscribe to this mod's changes

plan is a command published in the GitHub repository Done-0/openarche (12 stars, last pushed 4mo ago), licensed MIT. It adds 8 tokens to every session and 295 once invoked, about $0.0000 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 2026-08-30.