aa-plan-epic

aa-plan-epic is a skill for Claude Code from Peeyushmeher/agent-agile. It costs 42 tokens per session (973 once invoked), scanned A, original, MIT.

A planning workflow for splitting the next roadmap epic into worker-ready story cards. A roadmap is the ordered plan for the project's larger pieces of work.

In plain words
What is it for?
Use it to plan the next epic, define shared contracts, arrange work into waves, and add extra design and data checks for interface work.
Why use it?
It turns a broad epic into tasks with defined boundaries, dependencies, and checks, reducing uncertainty during implementation.

Skill for Claude Code

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

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 plan the next epic, define shared contracts, arrange work into waves, and add extra design and data checks for interface work.

Compare 6 skills 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-plan-epic

README.md
[![agentmods](https://agentmods.dev/badge/skills/peeyushmeher/agent-agile/aa-plan-epic/github.svg)](https://agentmods.dev/skills/peeyushmeher/agent-agile/aa-plan-epic)
Your own site
<a href="https://agentmods.dev/skills/peeyushmeher/agent-agile/aa-plan-epic"><img src="https://agentmods.dev/badge/skills/peeyushmeher/agent-agile/aa-plan-epic/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for aa-plan-epic

Your own site · 80×15
<a href="https://agentmods.dev/skills/peeyushmeher/agent-agile/aa-plan-epic"><img src="https://agentmods.dev/badge/skills/peeyushmeher/agent-agile/aa-plan-epic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 973 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 $0.00042 $0.00973
Opus 5 $0.00021 $0.00487
Sonnet 5 $0.00008 $0.00195
Haiku 4.5 $0.00004 $0.00097

Measured 10d ago against content hash 6e2b04023a76, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

aa-plan-epic 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 10d 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.

skills/aa-plan-epic/SKILL.md · 24 lines

How it starts

The opening of the file, as written. The whole thing — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aa-plan-epic

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/planner.md sections "Slicing epics into stories" and "The worker-readiness test", playbooks/system.md section "The memory spine", and playbooks/critics.md section "Panel refresh", and follow them exactly; do not re-derive or improvise the slicing process. When the epic is a UI epic (its demo sentence describes something a person sees or clicks), also read playbooks/design.md and apply it: design directions before Wave 0 on the first UI epic with no design system (2–4 self-contained HTML mockups, pick recorded in .planning/DECISIONS.md, tokens into the contracts), and a data-verify contract on every UI story card.

Wiring

  1. Read exactly three files — the three-file epic-to-epic read rule from "The memory spine": .planning/PROJECT.md, .planning/ROADMAP.md, and the previous epic's LEARNINGS.md. Read nothing else from prior epics, with the memory spine's two slicing-time exceptions: read .planning/DECISIONS.md when it exists (settled decisions carry forward, never re-opened), and run one targeted grep across all prior epics' LEARNINGS.md for this epic's files and topics — a search, never a read-everything; bake any hits into the story cards.
  2. Identify the next pending epic on the roadmap.
  3. Slice it into story cards per playbooks/planner.md "Slicing epics into stories": enumerate every shared artifact, assign each one to Wave 0 or to exactly one story, pairwise-check every story's file list against every other story's in the same wave for overlap, and assign waves — Wave 0 (contracts and shared setup), Wave 1 (parallel stories with no cross-story reads), Wave 2 (integration, with an epic-level acceptance check tied to the demo sentence).
  4. Write each story card to .planning/epics/EPIC-NN/stories/S*.md from playbooks/templates/STORY.md — one file per story, exactly the five fields: Goal, Files it owns, Acceptance check, Grader, Contracts consumed. Split a story only for parallel width or fresh-mind verification, per playbooks/planner.md "Slicing epics into stories" — never because two things merely feel like separate concerns.
  5. Run the worker-readiness test from playbooks/planner.md "The worker-readiness test" against every card in the epic — no sampling. A card that fails gets split, sharpened, or has its ambiguity moved into Wave 0's CONTRACTS.md. Do not report the epic sliced while any card still fails the test.
  6. Panel refresh check. If ROADMAP.md holds 5 or more epics and the epic just sliced sits in the 4th, 7th, 10th … row position (current row order, re-derived now, never stored), run the panel refresh per playbooks/critics.md "Panel refresh": read .planning/CONFIG.md for the smart tier (the deliberate, narrow exception to step 1's three-file rule), spawn aa-critic-spec and aa-critic-execution as parallel fresh subagents with standard panel inputs, fix every BLOCK inline with the affected critic re-run once, and route FLAGs by gate mode as the playbook defines. A BLOCK still standing after the re-run stops an autopilot run with a STATE.md update, exactly like a circuit breaker. Run the KR-drift tripwire against the LEARNINGS.md already in hand from step 1.
  7. Update .planning/STATE.md: phase set to the new epic's wave, what's in progress, the next action, and pointers to the files the next session must read.

Read the full file on GitHub · 24 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. 10d ago First seen · 24 lines · 42 tokens per session scan A 6e2b04023a76

Subscribe to this mod's changes

aa-plan-epic is a skill published in the GitHub repository Peeyushmeher/agent-agile (3 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 973 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 skills, from other repositories

project-manager

This skill has been upgraded with agentic AI capabilities, OKR/KPI integration patterns, and async-first workflows based on 2026 PM best practices research.

buiphucminhtam/forgewright · 68 tokens

team-okrs

An OKR tracking page for a quarter. OKRs, or objectives and key results, are goals paired with measurable results.

nexu-io/html-anything · 23 tokens

product-frameworks

Product management frameworks for business cases, market analysis, strategy, prioritization, OKRs/KPIs, personas, requirements, and user research. Use when building ROI projections, competitive analysis, RICE scoring, OKR trees, user personas, PRDs, or usability testing plans.

yonatangross/orchestkit · 61 tokens

gr-product-dev-ops

🇺🇸 Your dev team ships features nobody asked for while user-reported bugs pile up for months. Operations blames engineering for ignoring users; engineering blames operations for not understanding technical constraints. This gives you the complete Product × Engineering × Operations alignment SOP — from unified…

Gingiris-1031/gingiris-skills · 576 tokens

derive-capacity

Work out how many points a week each person on the aeman board actually gets through, from the cards they have closed, and set it as their capacity after the lead confirms. Use when a team lead asks about throughput, weekly capacity, how much a person or a team can take, or wants the numbers over the columns filled in.

aenix-io/aeman · 72 tokens

size-cards

Size the unsized cards of a team or a person on the aeman board — S/M/L/XL by a fixed rubric, written back through the aeman MCP after the lead confirms. Use when a team lead asks to estimate, size or weigh cards, or before a planning meeting.

aenix-io/aeman · 63 tokens