An iteration-planning meeting for an Agile Markdown backlog, where the team chooses work based on priority and its usual amount of work per iteration.

It helps identify committed stories, list work below the cutoff, total the planned points, and flag oversized or otherwise problematic items.

It makes the iteration commitment visible and highlights stories that need attention before work begins.

How mreider/agilemarkdown configures Claude Code

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-plan/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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mreider/agilemarkdown/am-plan/github.svg)](https://agentmods.dev/skills/mreider/agilemarkdown/am-plan)

Your own site

<a href="https://agentmods.dev/skills/mreider/agilemarkdown/am-plan"><img src="https://agentmods.dev/badge/skills/mreider/agilemarkdown/am-plan/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mreider/agilemarkdown/am-plan"><img src="https://agentmods.dev/badge/skills/mreider/agilemarkdown/am-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 690 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.

Model	Per session	Once invoked
Fable 5.1	$0.00071	$0.00690
Opus 5.5	$0.00028	$0.00276
Sonnet 5.5	$0.00014	$0.00138
Haiku 4.5	$0.00007	$0.00069

Measured 2mo ago against content hash 47579ca8998e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

am-plan 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 2mo 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-plan/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

am-plan

The IPM is the short conversation at the start of each iteration where the team commits to the work. The commit is implicit: it is the rank order of _priority.md at the moment the iteration starts.

When this fires

Human says "let's plan", "run IPM", "what's the iteration".
New iteration is starting.
User invokes /am-plan.

What to do

Identify the backlog. If multiple, ask which. Most projects have one.
Call sprint_plan(backlog=<name>). The tool returns the rank order, divided into committed (top of priority up to rolling velocity) and below-line (the rest), plus warnings on stories that need attention before the iteration starts.

Render the result to the human in a clear shape:

Iteration plan: <backlog>   velocity <N> / iteration

Committed:
  1. ★  <title>            <type>  <pts>p
  2. ●  <title>            <type>  <pts>p
  ...

Below the line:
  <next 3-5 stories>

Committed: <total> pts. Velocity: <N>. <Fits | Over by N pts>.

Surface warnings explicitly. The common ones:
- Oversized feature: a feature has an estimate above 8. Offer to call the am-decompose skill to split it.
- Unestimated feature: a feature has no estimate. Ask the human for a Fibonacci value (1, 2, 3, 5, 8). Pivotal pattern: point by uncertainty, not by hours.
- Overcommit: committed points exceed rolling velocity. Offer to trim from the bottom of the committed set.
Wait for the human's response. Loop on edits: the human edits _priority.md (re-rank) or asks you to fix a story; you re-call sprint_plan; you re-render. The loop ends when the human is satisfied with the plan as rendered.
The commit moment is implicit. The human says "let's go," or the human starts pulling the first story. Do not write a separate commit artifact.

What NOT to do

Do not invent estimates. If a story has no estimate, ask the human for one. Do not set one and move on.
Do not propose splitting a story without offering to call am-decompose. The decompose skill is the right tool; use it.
Do not pull a story (set_status started) during planning. The planning ceremony is a review; the iteration starts when the human pulls the first story afterwards.

Read the full file on GitHub · 76 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.

2mo ago First seen · 76 lines · 71 tokens per session scan A 47579ca8998e

Subscribe to this mod's changes

am-plan is a skill published in the GitHub repository mreider/agilemarkdown (8 stars, last pushed 4mo ago), licensed MIT. It adds 71 tokens to every session and 690 once invoked, about $0.0003 per session on Opus 5.5. 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.

Planning Project management agile markdown product-management scrum

am-plan next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
am-planmreider/agilemarkdown	Skill	8	4mo ago	MIT	A	71	Claude Code
gr-product-dev-opsGingiris-1031/gingiris-skills	Skill	89	2d ago	MIT	A	576	Claude Code, Codex
scrumboy-board-operatormarkrai/scrumboy	Skill	448	yesterday	AGPL-3.0	A	51	Claude Code
pm-skillsmrDesign-ww/vault-os	Skill	3	9d ago	MIT	A	179	Claude Code
productspecgokulrajaram/ProductSpec	Skill	317	3mo ago	MIT	A	35	Claude Code, Codex
productspec-authoringgokulrajaram/ProductSpec	Skill	317	3mo ago	MIT	A	90	Claude Code, Codex
project-managerbuiphucminhtam/forgewright	Skill	49	6d ago	none	A	68	Claude Code

agilemarkdown: Skill for Claude Code