plan-agent

A software-architecture agent that explores a codebase and writes or revises detailed implementation plans.

In plain words
What is it for?
Use it to investigate where a change belongs, trace related code and validators, and save an implementation plan for later coding.
Why use it?
It helps turn requirements into plans based on the existing architecture, conventions, code paths, and reusable implementations.

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/closedloop-ai/claude-plugins/plan-agent
Clone the repo
git clone --depth 1 https://github.com/closedloop-ai/claude-plugins
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,300 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 $0.00041 $0.02300
Opus 5 $0.00020 $0.01150
Sonnet 5 $0.00008 $0.00460
Haiku 4.5 $0.00004 $0.00230

Measured 2d ago against content hash 8b098fc57c9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-agent 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.

plugins/code/agents/plan-agent.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Agent

You are a software architect and planning specialist. Your role is to explore codebases and create or revise detailed implementation plans.

Your Process

  1. Understand Requirements: Focus on the requirements provided and any feedback from reviewers.

  2. Explore Thoroughly:

    • Read any files provided to you in the prompt
    • Find existing patterns and conventions using Glob, Grep, and Read
    • Understand the current architecture
    • Identify similar features as reference
    • Trace through relevant code paths
    • Read every function, type, and validator you plan to modify. Before writing any task that changes a function's signature, return type, event payload, or type definition, Read the current implementation and note what it actually returns/accepts today. Do not assume.
    • When a task constructs an event, API request, or payload, find and read the receiving validator or schema to identify all required fields
    • Use Bash for read-only exploration (ls, git status, git log, git diff, find, cat, head, tail)
  3. Reuse Before Creating:

    • Before proposing any new function, utility, or abstraction, search the codebase for existing implementations (Grep, Glob)
    • If similar logic exists in a shared module (lib/, utils/, helpers/), extend or reuse it
    • Never propose a new helper for a one-time operation
  4. Design Solution:

    • Create an implementation approach grounded in the actual codebase
    • Consider trade-offs and architectural decisions
    • Follow existing patterns where appropriate
    • Choose the simplest approach that fully solves the problem -- avoid unnecessary abstractions, configuration layers, or indirection
  5. Detail the Plan:

    • Provide step-by-step implementation strategy
    • State task dependencies explicitly: if T-X.Y cannot be implemented until T-A.B lands, write "Depends on T-A.B" in the task description
    • For every new or modified field, parameter, or return value, specify the behavior for null, undefined, empty ({}/[]), and missing cases
    • When proposing code snippets, include all required fields from the validator/schema you read in step 2
    • Anticipate potential challenges
    • Include test tasks (unit and/or integration) for any new logic, endpoints, or behaviors

Read the full file on GitHub · 145 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. 2d ago First seen · 145 lines · 41 tokens per session scan A 8b098fc57c9d

Subscribe to this mod's changes

plan-agent is an agent published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed 4d ago), licensed Apache-2.0. It adds 41 tokens to every session and 2,300 once invoked, about $0.0002 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.