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.
curl -O https://raw.githubusercontent.com/mreider/agilemarkdown/master/.claude/skills/am-decompose/SKILL.mdgit clone --depth 1 https://github.com/mreider/agilemarkdownWrote 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.
[](https://agentmods.dev/skills/mreider/agilemarkdown/am-decompose)<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>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.
| Model | Per session | Once 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 |
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.
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
-
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.
-
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.
-
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
-
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. -
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) ... -
Wait for the human's go-ahead. Do not call
create_itemuntil the human signs off on the breakdown. Once they do, create each story in order usingcreate_item, thenset_estimate, thenset_descriptionto 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.
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.
- 8d ago First seen · 78 lines · 60 tokens per session scan A d0dd26b4b6bc
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.
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…
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.
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…
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.
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…
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.