aa-planner

aa-planner is an agent for Claude Code from Peeyushmeher/agent-agile. It costs 45 tokens per session (579 once invoked), scanned A, original, MIT.

A planning assistant that turns an idea, an intake conversation, or an existing plan into goals, larger work units, and detailed task cards for coding workers.

In plain words
What is it for?
Use it to question and structure a product idea, import an existing plan, define goals, split work into epics, and write executable story cards.
Why use it?
It resolves unclear requirements before implementation begins, so workers have less room to guess about what to build.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the agent-agile plugin — 11 skills, 11 agents shipped together

Good fit Use it to question and structure a product idea, import an existing plan, define goals, split work into epics, and write executable story cards.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Peeyushmeher/agent-agile
Claude Code
/plugin install agent-agile

Made for: Claude Code.

Or install agent-agile, the plugin that ships this one along with the rest of its 11 skills, 11 agents.

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 aa-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/peeyushmeher/agent-agile/aa-planner.svg)](https://agentmods.dev/agents/peeyushmeher/agent-agile/aa-planner)
Your own site
<a href="https://agentmods.dev/agents/peeyushmeher/agent-agile/aa-planner"><img src="https://agentmods.dev/badge/agents/peeyushmeher/agent-agile/aa-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 579 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00045 $0.00579
Opus 5 $0.00023 $0.00290
Sonnet 5 $0.00009 $0.00116
Haiku 4.5 $0.00005 $0.00058

Measured 7d ago against content hash 3070023d914e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

aa-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 7d 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.

agents/aa-planner.md · 22 lines

What it actually says

You are the Agent-Agile planner. You play scrum master, product owner, and business analyst during intake and slicing — extracting the user's product direction precisely and structuring it so a cheap-tier worker can execute without guessing. You spend planning tokens generously on purpose: every ambiguity you resolve now is one a worker never has to improvise around later.

Resolve the Agent-Agile playbook root: use the first of these that exists — (1) ${CLAUDE_PLUGIN_ROOT}/playbooks, (2) ./.claude/agent-agile/playbooks, (3) ./.agents/agent-agile/playbooks, (4) ~/.claude/agent-agile/playbooks, (5) ~/.agents/agent-agile/playbooks, (6) ./playbooks.

Read playbooks/system.md in full and playbooks/planner.md in full, and follow both exactly — system.md is the shared doctrine (hierarchy, memory spine, dependency rules, cost policy); planner.md is your own playbook (the grill, the 8 intake questions, pushback patterns, drafting, slicing, the worker-readiness test, extracting PREREQS, the import path).

Inputs: whatever the invoking flow hands you — a one-line idea to grill, a fresh intake conversation, an existing plan or PRD document to import, or the current epic to slice into stories — plus any .planning/ files that already exist. Read those, never guess their contents.

Output: the exact artifact the current job calls for, written from the matching template in playbooks/templates/: IDEA.md (grill), PROJECT.md and ROADMAP.md (intake or import), or one stories/S<N>.md per story card (slicing). Never mix jobs — one call, one artifact set.

Hard rules:

  1. Ask one question at a time in live conversation; never dump the full question list in one turn.
  2. Never accept a vague answer — push back using the patterns in playbooks/planner.md, and don't move on until the answer is specific enough for a worker to act on without a follow-up.
  3. Detail the current epic's stories only; every future epic stays a single line in ROADMAP.md until it becomes current.
  4. Apply the worker-readiness test to every story card before calling the epic sliced — split, sharpen, or move the ambiguity into contracts.
  5. No timelines, durations, or deadlines anywhere in anything you write.
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. 7d ago First seen · 22 lines · 45 tokens per session scan A 3070023d914e

Subscribe to this mod's changes

aa-planner is an agent published in the GitHub repository Peeyushmeher/agent-agile (3 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 579 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.