rad-plan

rad-plan is a command for Claude Code from seanrreid/RAD_framework. It costs 76 tokens per session (2,311 once invoked), scanned A, original, MIT.

A command that researches and plans a feature or bug fix within defined agent responsibilities. It creates a wave-based plan on a separate work branch for later implementation.

In plain words
What is it for?
Use it to plan changes such as loading states, timezone fixes, or CSV export. It researches the codebase, writes the plan, creates the work branch, and commits the plan there.
Why use it?
It keeps research summaries out of the main working context and prevents planning changes from being mixed with the default branch. It also makes role limits and outside dependencies explicit.

Command for Claude Code

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/seanrreid/rad_framework/rad-plan
Clone the repo
git clone --depth 1 https://github.com/seanrreid/RAD_framework

Made for: Claude Code.

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 rad-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/seanrreid/rad_framework/rad-plan.svg)](https://agentmods.dev/commands/seanrreid/rad_framework/rad-plan)
Your own site
<a href="https://agentmods.dev/commands/seanrreid/rad_framework/rad-plan"><img src="https://agentmods.dev/badge/commands/seanrreid/rad_framework/rad-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,311 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 $0.00076 $0.02311
Opus 5 $0.00038 $0.01156
Sonnet 5 $0.00015 $0.00462
Haiku 4.5 $0.00008 $0.00231

Measured 4d ago against content hash 8f2d9dc023dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rad-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 4d 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.

.claude/commands/team/rad-plan.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/rad-plan

Research and plan a feature within your agent boundaries. The plan doc lives on its own rad/[feature] work branch (Lane B): nothing is committed to the default branch here. The architect approves with /rad-approve — there is no plan PR. The plan and its code reach the default branch later, together, via the single deliver PR.

Input

$ARGUMENTS should describe the feature or bug fix. Examples:

  • "Add skeleton loading states to the habit list"
  • "Fix the date picker not respecting user timezone"
  • "Add export to CSV for the weekly summary"

If $ARGUMENTS is empty, ask for a description before proceeding.


Process

Step 1: Determine role and available agents

Read CLAUDE.md to find:

  • The current user's role (developer or designer)
  • The Agent Scope Map
  • Which agents are available for this role

Only call agents available to your role. If a feature requires an agent outside your role's scope, note it in the plan as a dependency requiring architect involvement.

Step 2: Delegate research to an Explore sub-agent

Spawn an Explore sub-agent with the prompt below. Fill in all bracketed values before calling. Do not read files directly in main context — the sub-agent returns bounded summaries; use those to write the plan.

You are researching a codebase to support a feature plan. Return bounded
summaries only — no raw file dumps. Cap each file summary at 15 lines.
Stop after 10 searches total regardless of what remains.

Feature: [feature description from $ARGUMENTS]
Role scope: [agent scope for this role from CLAUDE.md Agent Scope Map]

Research goals:
1. Find the files most likely touched by this feature (entry points, components,
   models, routes, tests — whatever is relevant to the stack)
2. For each file found, summarize: what it does, approximate line count,
   which lines are relevant to this feature
3. Identify any shared infrastructure, auth modules, or files this feature
   must not touch
4. Note any existing patterns (naming, structure, test conventions) the
   implementation should follow

Return format — output this block and nothing after it:

RESEARCH_SUMMARY
feature: [feature name]
searches_used: [N] of 10

files:
  - path: [file path]
    lines: [approximate line count]
    relevant_lines: [range or "throughout"]
    summary: [1–2 sentences: what it does and what changes for this feature]

do_not_touch:
  - [path] — [why]

patterns:
  - [observed pattern the plan should follow]

out_of_scope_flags:
  - [anything that signals this feature may cross agent scope boundaries]
END_RESEARCH_SUMMARY

Read the full file on GitHub · 276 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. 4d ago First seen · 276 lines · 76 tokens per session scan A 8f2d9dc023dd

Subscribe to this mod's changes

rad-plan is a command published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 9d ago), licensed MIT. It adds 76 tokens to every session and 2,311 once invoked, about $0.0004 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.