aimeat-protocol: Skill for Claude Code

.claude/skills/aimeat-library-authoring/SKILL.md

aimeat-library-authoring is a skill for Claude Code from miikkij/aimeat-protocol. It costs 0 tokens per session (1,718 once invoked), scanned A, original, MIT.

A set of AIMEAT rules for creating shared code, including browser libraries, node-side extensions, and packaged third-party libraries.

In plain words
What is it for?
Use it before editing SDK libraries, Cortex libraries, extensions, or library packs to choose the correct source layout, build process, and delivery path.
Why use it?
It prevents shared code from being placed in the wrong directory or served through the wrong URL, which can make it unavailable to the application.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is miikkij/aimeat-protocol's own configuration. It tells Claude Code how to work on aimeat-protocol 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 aimeat-protocol configures →

Reuse

Borrowing it

Nothing to install: this file belongs to miikkij/aimeat-protocol. 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/miikkij/aimeat-protocol/main/.claude/skills/aimeat-library-authoring/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/miikkij/aimeat-protocol

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 aimeat-library-authoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/miikkij/aimeat-protocol/aimeat-library-authoring/github.svg)](https://agentmods.dev/skills/miikkij/aimeat-protocol/aimeat-library-authoring)
Your own site
<a href="https://agentmods.dev/skills/miikkij/aimeat-protocol/aimeat-library-authoring"><img src="https://agentmods.dev/badge/skills/miikkij/aimeat-protocol/aimeat-library-authoring/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 aimeat-library-authoring

Your own site · 80×15
<a href="https://agentmods.dev/skills/miikkij/aimeat-protocol/aimeat-library-authoring"><img src="https://agentmods.dev/badge/skills/miikkij/aimeat-protocol/aimeat-library-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,718 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 $0.00000 $0.01718
Opus 5 $0.00000 $0.00859
Sonnet 5 $0.00000 $0.00344
Haiku 4.5 $0.00000 $0.00172

Measured 4d ago against content hash 4ab28b4dca8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

aimeat-library-authoring 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.

.claude/skills/aimeat-library-authoring/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Authoring shared code

Four kinds of shared code, four different homes. Putting one in the wrong place is the recurring mistake, so start by naming which one you are writing.

Kind Runs where Source Reached as
Served SDK lib the browser src/static/sdk-libs/<name>/ (ESM) /v1/libs/aimeat-<name>.js
Cortex lib the browser its own package, installed on the node /v1/cortex/<pack>/libs/<file>.js
Extension the node, QuickJS WASM sandbox manifest + scripts/ /v1/ext/<name>/<action>
Library pack the browser (vendored third-party) public/lib/ + registry entry /lib/<name>@<major>.js

Two prefixes, never mixed: AIMEAT SDK libs load from /v1/libs/, vendored styling and third-party packs from /lib/. Mixing them 404s.

Served SDK libs (/v1/libs/aimeat-*.js)

29 libs today. Authored as componentized, JSDoc-typed ESM under src/static/sdk-libs/<name>/, sharing code through _core/, under 800 lines per file, esbuild-bundled to a classic IIFE with pnpm build:sdk, and served with a per-node config prelude by src/routes/libs.ts. Guarded by check:sdk (bundle in sync with sources) and typecheck:sdk, both in the pre-commit hook.

  • Never author a served lib as JavaScript inside a TypeScript template string. That was the old lib-*.ts / auth-lib-part*.ts pattern, removed 2026-07-19. Edit the ESM source and rebuild.
  • No backticks in a served lib's JSDoc while any template-string path remains. A stray one closes the literal and typecheck fails with TS1005.
  • The bundle is cached: restart the dev server or you are testing the previous build.
  • A lib is the right home for behaviour every app would otherwise re-implement. When an app needs something the platform should own, fix the lib rather than the app; the fix then reaches every app.

Cortex libs

Browser IIFE installed on the node as a pack (manifest + libs/). The manifest wants spec.version, a filename, and a string api_surface; it serves from the bare name.

Read the full file on GitHub · 98 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. 4d ago Changed · +8 lines 4ab28b4dca8a
  2. 10d ago First seen · 90 lines · 0 tokens per session scan A df9ae0d1056c

Subscribe to this mod's changes

aimeat-library-authoring is a skill published in the GitHub repository miikkij/aimeat-protocol (7 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,718 tokens. 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

coordinate-agent-work

Coordinate independent coding or research agents across host sessions and linked Git worktrees through AgentTool Collab's local journal. Use when starting or resuming credential-bound coordination, publishing optional self-declared presence, splitting parallel work, preventing overlapping edits, polling or…

cambridgetcg/agenttool · 95 tokens

capability-conductor

A guide for finding and combining existing agent skills for one task while keeping track of where each skill came from and what limits it has.

cambridgetcg/agenttool · 107 tokens

nen-math-card

Frame a mathematical challenge as a bounded proof, model, or measurement inquiry and decide whether it can construct, repair, choose, or clarify anything. Use when a user asks whether a math problem is useful, wants to turn a competition or puzzle into reusable understanding, needs to separate formal proof from world…

cambridgetcg/agenttool · 94 tokens

scriptwriter

Use when the user wants to interact with the decentralised scriptwriter recognition + co-brainstorm protocol — opening REAL RECOGNISE REAL cascades, creating writers' rooms, contributing scenes/dialogue/twists to a draft, pairing with peer scriptwriter nodes, or drawing chaos cards. Triggers on phrases like "open a…

cambridgetcg/agenttool · 123 tokens

nen-common-ground

Model several explicitly stated decision boundaries as convex feasible regions and return either shared room, a small conflict witness, or an honest refusal of the model. Use when the user invokes Helly, common-ground geometry, 共域, local-to-global agreement, constraint reconciliation, or a KINGDOM challenge about…

cambridgetcg/agenttool · 84 tokens

scriptwriter-room

Focused on writers' room operations — creating rooms with a seed prompt, contributing signed scenes/dialogue/stage-directions/twists/chaos-cards/notes, subscribing to the SSE live stream, polling for new contributions. Use when the user wants to actually draft something with peers, draw a chaos card to seed a scene…

cambridgetcg/agenttool · 97 tokens