agilemarkdown: Skill for Claude Code

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

am-align is a skill for Claude Code from mreider/agilemarkdown. It costs 79 tokens per session (694 once invoked), scanned A, original, MIT.

A pre-coding check for an Agile Markdown story, where the coding agent explains its understanding and asks the product manager to confirm it.

In plain words
What is it for?
It helps select one backlog story, check it against project goals, summarize what done means, and surface missing or conflicting details.
Why use it?
It reduces the risk of building the wrong feature because the agent must resolve unclear requirements before writing code.

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-align/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-align

README.md
[![agentmods](https://agentmods.dev/badge/skills/mreider/agilemarkdown/am-align.svg)](https://agentmods.dev/skills/mreider/agilemarkdown/am-align)
Your own site
<a href="https://agentmods.dev/skills/mreider/agilemarkdown/am-align"><img src="https://agentmods.dev/badge/skills/mreider/agilemarkdown/am-align.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 694 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 $0.00079 $0.00694
Opus 5 $0.00039 $0.00347
Sonnet 5 $0.00016 $0.00139
Haiku 4.5 $0.00008 $0.00069

Measured 6d ago against content hash 4a791caacb1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

am-align 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 6d 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-align/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

am-align

The agent is the dev pair. Before the dev pair writes code on a story, the dev pair restates the story in its own words and asks the PM to confirm. With humans, this was pair programming. With an AI in the dev-pair seat, this is the safeguard against the central failure mode of agent coding: the agent that confidently builds the wrong feature.

When this fires

  • The user says any of: "let's pull X", "start X", "I want to work on X", "what's next", or invokes /am-align.
  • The agent is about to call set_status(path, "started") on a feature. Fire this skill first.

What to do

  1. Identify the story path. Use next_item if no path was given. Insist on exactly one path.

  2. Call get_item(path) for the frontmatter and body.

  3. Read inception.md if it exists. The story should fit the project's stated user, goal, and constraints; if the story does not, surface the conflict here, not after code is written.

  4. Restate the agent's reading of the story in one paragraph. Cover:

    • Who the user is (one line).
    • What the change is (one or two lines).
    • What done looks like, in concrete terms.
  5. Surface checkable ambiguities. Look for:

    • A statement that mentions a metric without a value ("fast", "many", "most").
    • A reference to another story not in the priority list.
    • An estimate missing, or above 8.
  6. Ask the PM: "anything to clarify before I pull?"

  7. If clarifications come back, use the right writer:

    • Body edit: set_description.
    • Different estimate: set_estimate.
    • Different priority: rank_item.
    • Wrong story altogether: leave it, return to step 1 with a different path.
  8. Once the PM is satisfied, call set_status(path, "started"). The dev pair is now actively working on the story.

What NOT to do

  • Do not write code before step 8. Alignment is the seam.
  • Do not invent new requirements in the restatement. If something is unclear, ask the PM rather than guessing.
  • Do not skip this skill on bugs or chores. They have their own conventions; restate the story in one line so the PM can confirm the agent has the right context.

Read the full file on GitHub · 75 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. 6d ago First seen · 75 lines · 79 tokens per session scan A 4a791caacb1b

Subscribe to this mod's changes

am-align is a skill published in the GitHub repository mreider/agilemarkdown (7 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 694 once invoked, about $0.0004 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