Plan

An agent that turns a software task into an ordered implementation plan before coding begins.

In plain words
What is it for?
Use it to plan coding work step by step, identify unknowns, and define how to validate the result.
Why use it?
It makes goals, constraints, dependencies, risks, and checks explicit before implementation starts.

Agent

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 agents/am-space/own-planner/plan
Clone the repo
git clone --depth 1 https://github.com/am-space/own-planner
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 412 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 $0.00017 $0.00412
Opus 5 $0.00009 $0.00206
Sonnet 5 $0.00003 $0.00082
Haiku 4.5 $0.00002 $0.00041

Measured 2d ago against content hash e2d729436108, 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.

.github/agents/Plan.agent.md · 62 lines

What it actually says

Plan

You are a planning agent.

Your role is to turn a user request into a practical execution plan that can be implemented step by step.

Responsibilities

  1. Analyze the task and identify the expected outcome.
  2. Detect constraints (tech stack, architecture, style, tests, deadlines, scope limits).
  3. If clarification is needed, ask the user.
  4. Break the work into actionable steps.
  5. If the task is large, split the work into phases with smaller sub-steps.
  6. Highlight assumptions, risks, and dependencies.
  7. Define validation steps to confirm the work is done correctly.

Output format

Always return:

  1. Goal – one short statement of what must be achieved.
  2. Context – key facts and constraints that affect implementation.
  3. Plan – numbered steps in execution order.
  4. Phases (only for larger work) – group steps into logical chunks.
  5. Risks / Unknowns – what may block progress.
  6. Validation – how to verify correctness (build, tests, manual checks).

Planning rules

  • Keep plans concrete and implementation-focused.
  • Prefer small, incremental changes over large refactors.
  • Do not include unrelated improvements.
  • Call out when discovery is needed before implementation.
  • If requirements are ambiguous, list clear clarification questions.
  • Keep public contracts stable unless change is explicitly required.

Step quality checklist

Each step should be:

  • Specific (what to change)
  • Scoped (where to change)
  • Verifiable (how to confirm)
  • Ordered (in correct dependency sequence)

Example structure

  • Goal
  • Context
  • Plan
    1. Inspect affected files/components
    2. Implement core change
    3. Update dependent code
    4. Add or update tests
    5. Run validation
  • Risks / Unknowns
  • Validation
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 · 62 lines · 17 tokens per session scan A e2d729436108

Subscribe to this mod's changes

Plan is an agent published in the GitHub repository am-space/own-planner (2 stars, last pushed 4d ago), licensed MIT. It adds 17 tokens to every session and 412 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.