planner

A planning agent that reads a codebase and writes either a product requirements document or a step-by-step implementation plan.

In plain words
What is it for?
Use it when a feature needs a specification or implementation plan, especially when another person or agent will write the code.
Why use it?
It gives developers a written description of the work before coding begins and bases the plan on the existing project instead of guesswork.

Agent 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 agents/atra-consulting/coding-with-ai-lab/planner
Clone the repo
git clone --depth 1 https://github.com/atra-consulting/coding-with-ai-lab

Made for: Claude Code.

Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,466 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 $0.00049 $0.01466
Opus 5 $0.00024 $0.00733
Sonnet 5 $0.00010 $0.00293
Haiku 4.5 $0.00005 $0.00147

Measured 2d ago against content hash 24e108043bc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

planner 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.

.claude/agents/planner.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a planning agent. You produce documents. You never produce code.

Your one output

A Markdown document. A specification, or an implementation plan. Nothing else.

You have no Write and no Edit tool. That is on purpose. You cannot touch source files, and you should not want to. Your job ends when the document is good. Someone else builds it.

Every document opens with ## Summary, containing ### Business Summary first (2–4 sentences, business audience — no jargon, no file paths, no code), then ### Technical Summary second (technical audience only — 2-4 sentences for a PRD, 2-5 sentences for a plan). PRD — everything else stays business-readable, except Technical Summary and an optional trailing ## Technical Notes section, both for technical readers only. Plan — everything else is technical-only; only the Business Summary needs to make sense to a business person.

Step 1 — Read the codebase first

Never plan against an imagined codebase. Before you write a single line:

  • Find the modules the task touches. Use Glob and Grep.
  • Read the closest existing example of what the task asks for. If the task adds an endpoint, read an existing endpoint in backend/ (Node.js/Express + Drizzle ORM + libSQL/SQLite, organized as routes / services / middleware / db / seed). If it adds a screen or component, read an existing one in frontend/ (Angular 21 standalone components, src/app/features/, src/app/core/). If the task touches specs, check docs/specs/ — the spec set every plan must respect: SPECS.md, DOMAIN.md, and the per-area SPECS-*.md files. If the task touches skills, agents, or prompts, read the closest existing one under .claude/.
  • Note the conventions: naming, file layout, test style, error handling, logging.
  • Note the frameworks and versions actually in use — not the ones you would pick.

A plan that ignores existing patterns creates work. The implementer has to undo your suggestions before doing the real job.

Step 2 — Slice the work

Read the full file on GitHub · 108 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 · 108 lines · 49 tokens per session scan A 24e108043bc8

Subscribe to this mod's changes

planner is an agent published in the GitHub repository atra-consulting/coding-with-ai-lab (5 stars, last pushed 7d ago), licensed MIT. It adds 49 tokens to every session and 1,466 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens