create-aip

create-aip is a skill for Claude Code, Codex from RobLovesTech/AgenticFlyWheel. It costs 48 tokens per session (806 once invoked), scanned A, original, MIT.

A guided workflow for creating or updating an Agent Implementation Packet, a written plan that defines a feature's scope, requirements, and verification.

In plain words
What is it for?
Use it to start a feature packet, document acceptance criteria and risks, and prepare work for implementation.
Why use it?
It turns an unclear feature request into agreed work that agents can implement and check without silently guessing important decisions.

Skill for Claude CodeCodex

Part of the agentic-flywheel plugin — 6 skills shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/roblovestech/agenticflywheel/create-aip
Any agent
npx skills add RobLovesTech/AgenticFlyWheel --skill create-aip
Clone the repo
git clone --depth 1 https://github.com/RobLovesTech/AgenticFlyWheel

Made for: Claude Code, Codex.

Or install agentic-flywheel, the plugin that ships this one along with the rest of its 6 skills.

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 create-aip

README.md
[![agentmods](https://agentmods.dev/badge/skills/roblovestech/agenticflywheel/create-aip.svg)](https://agentmods.dev/skills/roblovestech/agenticflywheel/create-aip)
Your own site
<a href="https://agentmods.dev/skills/roblovestech/agenticflywheel/create-aip"><img src="https://agentmods.dev/badge/skills/roblovestech/agenticflywheel/create-aip.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 806 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00048 $0.00806
Opus 5 $0.00024 $0.00403
Sonnet 5 $0.00010 $0.00161
Haiku 4.5 $0.00005 $0.00081

Measured 4d ago against content hash 1e67aa36941d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-aip 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 4d 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.

templates/claude-plugin/agentic-flywheel/skills/create-aip/SKILL.md · 40 lines

What it actually says

Create or update an Agent Implementation Packet for $ARGUMENTS.

Persona:

  • Act as the AIP Collaboration Steward. Be active, precise, and protective of user intent.
  • Do not silently decide goals, scope, acceptance, contracts, rollout, risks, or verification.

Process:

  1. Detect the AFW layout in the current repo.
  2. Read AGENTS.md first.
  3. Prefer these sources:
    • prompts/AIP_COLLAB.md or AgenticFlywheel/prompts/AIP_COLLAB.md
    • prompts/AIP_NEW.md or AgenticFlywheel/prompts/AIP_NEW.md
    • spec/AIP_FRAMEWORK.md, docs/AIP_FRAMEWORK.md, or AgenticFlywheel/spec/AIP_FRAMEWORK.md
    • templates/aip/* or docs/templates/AIP/*
    • templates/aip-lite/* or docs/templates/aip-lite/*
    • docs/features/REGISTRY.yaml when the installed docs layout exists
  4. Route the request before drafting:
    • Default generic requests like new AIP or create AIP to AIP_COLLAB.md.
    • Use AIP_NEW.md only when the user explicitly wants direct scaffolding or accepted prior planning artifacts already settle the requirements.
    • Treat accepted outputs from OFFICE_HOURS.md, AUTOPLAN.md, or REVIEWS.md as sufficient planning input when they cover the full collaboration readiness gate.
    • Treat a detailed feature request as seed context, not as accepted collaboration readiness.
  5. Choose lightweight vs full AIP using AFW scale guidance.
  6. Ask short, targeted rounds until goals, user/operator impact, all personas (with per-persona scope confirmation), scope, non-goals, priority tiers (for large features with 3+ capability areas), acceptance, contracts/data model, reference data completeness, cross-cutting behaviors (lifecycle, grandfathering, evaluation semantics, defaults, audit scope), interaction surfaces (user journey walkthrough), rollout, risks, verification, and the enabled vs omitted capability modules for full AIPs are confirmed or explicitly accepted as assumptions.
  7. Before writing, show the structured Collaboration Summary receipt, packet manifest assumptions (packet_level, requirements_mode, delivery_surfaces, enabled_modules, omitted_modules), packet path, planned files, and a concise diff preview.
    • Stop for user confirmation after showing the summary. Do not create packet files, mark collaboration-readiness complete, or implement in the same turn that first proposes the summary.
  8. Update or propose the related feature registry entry.
  9. Ensure full AIPs record the structured Collaboration Summary receipt in REVIEWS.md; ensure AIP-Lite records it in README.md.
  10. Ensure the packet includes collaboration-readiness, implementation audit, audit remediation, audit re-verification, and packet closure gates.
  11. For full AIPs, write packet_level, requirements_mode, delivery_surfaces, enabled_modules, and omitted_modules into CHECKLIST.yaml, scaffold only the enabled module docs/tasks, and generate initial AGENT_PROMPT.txt and IMPLEMENTATION_AUDIT_PROMPT.txt from the completed packet docs before the final diff preview and approval bundle.
  12. Tell the user that both prompt artifacts must be refreshed again during Docs & Handoff if implementation or audit remediation changes packet docs.

If the repo does not contain AFW, say so and stop unless the user wants you to bootstrap it first.

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. 4d ago First seen · 40 lines · 48 tokens per session scan A 1e67aa36941d

Subscribe to this mod's changes

create-aip is a skill published in the GitHub repository RobLovesTech/AgenticFlyWheel (2 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 806 once invoked, about $0.0002 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens