A command that sends research findings to a Planner agent, which creates a detailed implementation plan as a Markdown file. The plan is saved in the project’s configured plans folder.

Provide a goal, locate existing research, generate a plan, and optionally have a Critic agent annotate and the Planner revise it.

It turns research documents into an actionable development plan and can optionally request a critique before the plan is finalized.

plan — Command by brettbuddin

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/brettbuddin/claude-plugins/plan

Clone the repo

git clone --depth 1 https://github.com/brettbuddin/claude-plugins

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 531 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.

Model	Per session	Once invoked
Fable 5	$0.00028	$0.00531
Opus 5	$0.00014	$0.00266
Sonnet 5	$0.00006	$0.00106
Haiku 4.5	$0.00003	$0.00053

Measured yesterday against content hash 6825439e252b, 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 yesterday.

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.

smith/commands/plan.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan

Dispatch the Planner agent to produce an implementation plan.

Args

<specific goal description> (required). If no description is provided, reply with a short usage summary and stop.

Steps

Use the smith:config skill to read project configuration. Use the output_directory value (default: docs/) wherever <output_directory> appears below. Note the plan_auto_critique value (default: false) for step 4.
Glob for <output_directory>/research/*.md in the working directory.
Use the Task tool with subagent_type: "Planner" and run_in_background: false.
Prompt the agent with:
- The specific goal description provided by the user
- Which research file(s) exist (let the planner pick the right one per its own instructions)
If plan_auto_critique is true: a. Use the Task tool with subagent_type: "Critic" and run_in_background: false. Prompt the agent with the working directory path so it can find and annotate the plan file that was just created. b. After the Critic completes, use the Task tool with subagent_type: "Planner" and run_in_background: false. Prompt the agent with the working directory path and instruct it to read the plan file and address any inline annotations from the Critic.
After completion:
- If auto-critique ran: tell the user the plan has been critiqued and revised, provide the file path, and suggest they review it. Mention they can run /critique-plan and /revise-plan for additional rounds, or proceed to /implement.
- If auto-critique did not run: tell the user the plan file path (which will be <output_directory>/plans/GOAL.md) and suggest they review/annotate it, then run /critique-plan, /revise-plan, or /implement.

Prompting the Agent

When constructing the prompt for the Task tool, include:

The user's description
The working directory path so the agent knows where to find/write files
Any additional context the user provided in the conversation

Do NOT paste the agent's own instructions into the prompt; the agent definitions are already loaded by the Task tool via subagent_type.

Read the full file on GitHub · 39 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.

yesterday First seen · 39 lines · 28 tokens per session scan A 6825439e252b

Subscribe to this mod's changes

plan is a command published in the GitHub repository brettbuddin/claude-plugins (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 531 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.

Planning Research

plan

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Plan

Args

Steps

Prompting the Agent

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement