agilemarkdown: Skill for Claude Code

.claude/skills/am-decompose/SKILL.md

am-decompose is a skill for Claude Code from mreider/agilemarkdown. It costs 60 tokens per session (698 once invoked), scanned A, original, MIT.

A method for splitting a broad product idea into small Agile Markdown stories that can each be delivered independently.

In plain words
What is it for?
It helps restate the goal, find the smallest useful deliverable, propose two to five stories, and check their estimates.
Why use it?
It turns a vague request into manageable work and keeps each feature story within an eight-point estimate limit.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is mreider/agilemarkdown's own configuration. It tells Claude Code how to work on agilemarkdown itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agilemarkdown configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mreider/agilemarkdown. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mreider/agilemarkdown/master/.claude/skills/am-decompose/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mreider/agilemarkdown

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 am-decompose

README.md
[![agentmods](https://agentmods.dev/badge/skills/mreider/agilemarkdown/am-decompose.svg)](https://agentmods.dev/skills/mreider/agilemarkdown/am-decompose)
Your own site
<a href="https://agentmods.dev/skills/mreider/agilemarkdown/am-decompose"><img src="https://agentmods.dev/badge/skills/mreider/agilemarkdown/am-decompose.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 698 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 $0.00060 $0.00698
Opus 5 $0.00030 $0.00349
Sonnet 5 $0.00012 $0.00140
Haiku 4.5 $0.00006 $0.00070

Measured 8d ago against content hash d0dd26b4b6bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

am-decompose 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 8d 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/skills/am-decompose/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

am-decompose

The agent's job is to turn a problem statement into a small set of stories that pass two tests: each story is independently shippable, and each story is at or below 8 points.

When this fires

  • Human describes a goal that is bigger than a single story.
  • Human pastes a vague feature ask and wants stories.
  • User invokes /am-decompose.

What to do

  1. Read the problem out loud: restate it in two or three sentences so you and the human agree on what "done" would look like at the feature level.

  2. Identify the value seam: the smallest piece that, shipped on its own, is useful to the user. Not the easiest piece. Not the piece you want to write first. The piece that, in isolation, the PM could ship and the user would notice.

  3. Propose 2-5 stories. Each one:

    • has a one-sentence title
    • has a short body describing what the user-visible change is
    • has an estimate ≤ 8
    • is independently shippable
  4. Run coach_check(action="set_estimate", estimate=<your estimate>, type="feature") for each proposed estimate. If any returns refused with the 8-point cap, split that story further.

  5. Render the proposed stories to the human in this shape:

    1. <title> (<estimate> pts)
       <one or two lines describing the user-visible change>
       Why now: <one sentence on order>
    
    2. <title> (<estimate> pts)
       ...
    
  6. Wait for the human's go-ahead. Do not call create_item until the human signs off on the breakdown. Once they do, create each story in order using create_item, then set_estimate, then set_description to write the body.

Heuristics for splitting

  • Workflow split: if the feature has steps (e.g., user uploads, system processes, system notifies), each step can be its own story if it has a meaningful intermediate state.
  • Surface split: web flow vs API flow vs admin flow.
  • Spike first: if the team has never built anything close to this problem and confidence is low, the first story is a spike (a chore with a small fixed budget). It produces an artifact that lets the next stories be estimated honestly.
  • Happy path then edge: ship the happy path first; ship the failure modes as follow-up stories.

Read the full file on GitHub · 78 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. 8d ago First seen · 78 lines · 60 tokens per session scan A d0dd26b4b6bc

Subscribe to this mod's changes

am-decompose is a skill published in the GitHub repository mreider/agilemarkdown (7 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 698 once invoked, about $0.0003 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

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

productspec

Use when implementing, reviewing, planning, or changing work governed by a Product Spec. Treat .product-spec.md files as the product contract for the work.

gokulrajaram/ProductSpec · 35 tokens

productspec-authoring

Writes, validates, and converts ProductSpec files (.product-spec.md), the Markdown format for recording product intent before implementation. Use when authoring a new Product Spec, converting an existing PRD or feature doc into one, validating spec files locally or in CI, or recording how a spec's intent changed over…

gokulrajaram/ProductSpec · 90 tokens

scrumboy-board-operator

Operate Scrumboy projects and boards through MCP or Agoragentic APIs. Use when an agent needs to inspect board state, plan sprint work, create todos, move cards, manage tags, or summarize project health.

markrai/scrumboy · 51 tokens

pm-skills

Use when coordinating project-delivery work across the 8 project-management sub-skills — sprint/velocity analytics, portfolio health, Jira/JQL, Confluence, Atlassian admin, templates, meeting analysis, team comms. Triggers on 'our sprints feel off', 'project health report', 'audit our Jira permissions', 'when will it…

mrDesign-ww/vault-os · 179 tokens

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