What is am-inception?

A guided conversation for defining a new agilemarkdown project before planning its work. It records the user, goal, reason, success measure, constraints, and excluded work in an inception.md file.

Use it when starting a project, running an inception, or preparing an agilemarkdown repository for story planning.

Starting development without agreeing on these points can leave the team with unclear scope and conflicting expectations. This process turns the initial discussion into a shared project brief.

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-inception/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-inception/github.svg)](https://agentmods.dev/skills/mreider/agilemarkdown/am-inception)

Your own site

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

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 641 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	$0.00076	$0.00641
Opus 5.5	$0.00030	$0.00256
Sonnet 5.5	$0.00015	$0.00128
Haiku 4.5	$0.00008	$0.00064

Measured 2mo ago against content hash 6bf8dd7eb460, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

am-inception 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-inception/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

am-inception

An inception is the conversation that frames a project. The output is a one-page document at inception.md covering six sections. This skill runs the conversation; the human answers; the doc lands on disk.

When this fires

Human says "let's run an inception" or starts a new project.
Repo has no inception.md and the human is about to plan stories.
User invokes /am-inception.

What to do

Check whether inception.md already exists. Call inception_doc() (no body argument). If existed=true, ask the human whether to read the current doc or rewrite it. Default: read.
If the doc does not exist or the human wants to rewrite, walk the six questions one at a time. Ask each, wait, write the answer down. Do not move on until the human answers.
- The user. "Who, specifically, are we building this for? Not a demographic. A real person with real circumstances."
- The goal. "What changes for that user when we ship? Make it observable."
- The reason. "Why this, why now? What changes if we do not ship this?"
- Success. "How will we know it worked? The smallest signal you would believe."
- Constraints. "What can't move? Budget, deadline, regulator, dependency."
- Out of scope. "What are we explicitly not doing? Naming this saves arguments later."
Assemble the answers into the inception template shape (six ## headings with the human's text under each) and write the doc with inception_doc(body=<assembled body>).
Confirm: print the doc back to the human and ask whether to commit it (the human commits via git; you do not run git from the agent).

What NOT to do

Do not invent answers. If the human says "I don't know," that is the answer; record it and move on. The inception is more useful with honest gaps than with confident fabrications.
Do not write stories yet. The inception produces a one-pager. Stories come later, once the team is ready to plan the first iteration.
Do not skip the "Out of scope" section. It is the most useful one in retrospect. If the human says "nothing", push: "really, nothing? what are we deliberately not doing?"

Read the full file on GitHub · 71 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 · 71 lines · 76 tokens per session scan A 6bf8dd7eb460

Subscribe to this mod's changes

am-inception is a skill published in the GitHub repository mreider/agilemarkdown (8 stars, last pushed 4mo ago), licensed MIT. It adds 76 tokens to every session and 641 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 agile markdown product-management scrum

am-inception next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
am-inceptionmreider/agilemarkdown	Skill	8	4mo ago	MIT	A	76	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