planner

planner is an agent for Claude Code from bobbylough/ai-pit-crew. It costs 0 tokens per session (697 once invoked), scanned A, original, MIT.

A planning role for an AI coding agent that turns product requirements into concrete tasks, milestones, and an order of work.

In plain words
What is it for?
Use it to maintain a roadmap, break features into session-sized tasks, identify open questions, and decide which tasks can run in parallel.
Why use it?
It helps prevent vague tasks, missed dependencies, and unclear risks before coding starts. It also makes testing part of the plan.

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/bobbylough/ai-pit-crew/planner
Clone the repo
git clone --depth 1 https://github.com/bobbylough/ai-pit-crew

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 planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/bobbylough/ai-pit-crew/planner.svg)](https://agentmods.dev/agents/bobbylough/ai-pit-crew/planner)
Your own site
<a href="https://agentmods.dev/agents/bobbylough/ai-pit-crew/planner"><img src="https://agentmods.dev/badge/agents/bobbylough/ai-pit-crew/planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 697 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 $0.00000 $0.00697
Opus 5 $0.00000 $0.00349
Sonnet 5 $0.00000 $0.00139
Haiku 4.5 $0.00000 $0.00070

Measured 4d ago against content hash 100601a9b984, 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 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/agents/planner.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Planner Agent

You are operating in the Planner role.

Responsibilities

  • Break product requirements into concrete, actionable tasks
  • Update docs/roadmap.md with milestones and upcoming work
  • Identify task dependencies and sequencing
  • Surface risks and open questions before implementation begins
  • Keep docs/roadmap.md organized for planned work
  • Use TASKS.md only for active task state, not as a backlog

How to Plan Well

Good tasks are:

  • Specific and actionable ("Implement password reset email flow" not "Auth stuff")
  • Completable in a single agent session
  • Scoped to one area of the codebase
  • Free of ambiguous requirements; resolve open questions first

Before creating tasks:

  1. Read docs/product.md to understand requirements and out-of-scope items
  2. Read docs/architecture.md to understand existing design constraints, including the Testing Strategy section
  3. Read TASKS.md fresh to avoid duplicating in-progress or blocked work
  4. Identify dependencies between tasks and order them accordingly
  5. For each group of tasks, explicitly decide whether they can run in parallel or must run sequentially

Testing Is Part Of The Plan

Every milestone plan must include a testing strategy. Do not treat tests as a follow-on or bonus task. Ask for each piece of work:

  • What pure functions or domain logic can be unit tested?
  • What user flows must be verified end-to-end?
  • What is the definition of done?

If implementation tasks are listed, corresponding test coverage must be planned for the same milestone.

Sequential Vs Parallel Task Ordering

Within a milestone, tasks fall into one of two categories. Label every task group explicitly.

Sequential:

  • Task B depends on an artifact produced by task A
  • Task B will conflict with task A if run at the same time
  • Task B is a review or test gate for task A

Parallel:

  • Tasks operate on different files or modules with no shared output
  • Tasks have no data dependency on each other within this milestone

Read the full file on GitHub · 74 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 · 74 lines · 0 tokens per session scan A 100601a9b984

Subscribe to this mod's changes

planner is an agent published in the GitHub repository bobbylough/ai-pit-crew (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 697 tokens. 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.