~aod-blueprint

~aod-blueprint is a skill for Claude Code from davidmatousek/agentic-oriented-development-kit. It costs 98 tokens per session (4,048 once invoked), scanned A, a copy of ~aod-blueprint, MIT.

A project setup and story-generation workflow that detects whether a repository is new or already configured, then creates or updates its project work items.

In plain words
What is it for?
Use it to initialize a project, gather requirements, turn them into prioritized work items, create GitHub Issues, and produce project guides and a completion report.
Why use it?
It removes the need to run separate setup and planning steps, and avoids creating duplicate work items on later runs.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; names the AskUserQuestion tool.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash .aod/scripts/bash/create-issue.sh --title "{story_title}" --body "{formatted_body}" --stage discover.

Good fit Use it to initialize a project, gather requirements, turn them into prioritized work items, create GitHub Issues, and produce project guides and a completion report.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/davidmatousek/agentic-oriented-development-kit
agentmods
npx agentmods add skills/davidmatousek/agentic-oriented-development-kit/aod-blueprint

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 ~aod-blueprint

README.md
[![agentmods](https://agentmods.dev/badge/skills/davidmatousek/agentic-oriented-development-kit/aod-blueprint/github.svg)](https://agentmods.dev/skills/davidmatousek/agentic-oriented-development-kit/aod-blueprint)
Your own site
<a href="https://agentmods.dev/skills/davidmatousek/agentic-oriented-development-kit/aod-blueprint"><img src="https://agentmods.dev/badge/skills/davidmatousek/agentic-oriented-development-kit/aod-blueprint/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.

agentmods 80×15 button for ~aod-blueprint

Your own site · 80×15
<a href="https://agentmods.dev/skills/davidmatousek/agentic-oriented-development-kit/aod-blueprint"><img src="https://agentmods.dev/badge/skills/davidmatousek/agentic-oriented-development-kit/aod-blueprint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,048 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 $0.00098 $0.04048
Opus 5.5 $0.00039 $0.01619
Sonnet 5.5 $0.00020 $0.00810
Haiku 4.5 $0.00010 $0.00405

Measured 1mo ago against content hash fe7f400cf478, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

~aod-blueprint scanned grade A with 1 finding 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 1mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sf ${AOD_API_URL:-http://localhost:8000}/health -H "X-AOD-Source: skill"
Origin

This is a copy

100% identical to ~aod-blueprint — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/~aod-blueprint/SKILL.md · 419 lines

How it starts

The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/aod.blueprint Skill

Purpose

Unified project setup and story generation in a single command. The skill auto-detects whether the current project is new or existing, then runs the appropriate workflow:

  1. First-Run -- Creates GitHub repo, registers project with orchestrator API, activates it, runs interactive intake, generates stories, creates issues
  2. Subsequent-Run -- Skips setup, runs interactive intake, generates new stories with deduplication against existing issues
  3. Demo Mode (--demo) -- Loads pre-built Hello World stories from HELLO_WORLD_STORIES.md, skips interactive intake entirely

All modes end with issue creation, lifecycle sync, consumer guide generation, and a completion report.


Step 0: Prerequisites Check

Validate that required tools and services are available before proceeding.

0.1: Check gh CLI

Run gh --version via Bash tool.

  • If the command succeeds, continue to Step 0.2.
  • If the command fails, display the following error and STOP:
ERROR: GitHub CLI (gh) is not installed or not in PATH.
Install it from https://cli.github.com/ and run `gh auth login` to authenticate.

0.2: Check API Health

Run the following command via Bash tool:

curl -sf ${AOD_API_URL:-http://localhost:8000}/health -H "X-AOD-Source: skill"
  • If the command succeeds (exit code 0), display "Prerequisites OK" and continue to Step 1.
  • If the command fails, display the following error and STOP:
ERROR: AOD Orchestrator API is not reachable at ${AOD_API_URL:-http://localhost:8000}.
Start the API with `make run` and try again.

Step 1: Auto-Detection

Determine the project name, check for an existing project in the orchestrator, and set the execution mode.

1.1: Derive Project Name

Run git remote get-url origin via Bash tool.

  • If the command succeeds, extract the repo name from the URL: take the last path segment and strip any .git suffix. For example, https://github.com/org/my-project.git yields my-project. Store as {project_name}.
  • If the command fails (no remote configured), run basename $(pwd) via Bash tool and store the result as {project_name}.

Read the full file on GitHub · 419 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 1mo ago First seen · 419 lines · 98 tokens per session scan A fe7f400cf478

Subscribe to this mod's changes

~aod-blueprint is a skill published in the GitHub repository davidmatousek/agentic-oriented-development-kit (24 stars, last pushed 3mo ago), licensed MIT. It adds 98 tokens to every session and 4,048 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to ~aod-blueprint, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories