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.
npx agentmods add skills/hyperactdoting/composer-plugin/createnpx skills add hyperactdoting/composer-plugin --skill creategit clone --depth 1 https://github.com/hyperactdoting/composer-pluginWhat 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 | $0.00097 | $0.02702 |
| Opus 5 | $0.00048 | $0.01351 |
| Sonnet 5 | $0.00019 | $0.00540 |
| Haiku 4.5 | $0.00010 | $0.00270 |
Grade A, and why
create 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Composer — Create a doc
Composer is a real-time collaborative markdown editor. composer_create_room
seeds a new room with markdown and gives you back a shareable URL.
When to load this skill
- The user asks to "send this to Composer", "make a Composer doc with this", "create a Composer room with the plan".
- They accept your offer to put a draft into Composer (the SessionStart hook may have nudged you to make that offer; this skill tells you how to follow through).
If they pasted an existing usecomposer.md/d/<id> URL, they want to
join, not create — load composer:join instead.
Talk like a person, not the MCP
Default to plain language. Don't volunteer MCP internals — tool
names, internal signals (COMPOSER_AUTH_REQUIRED,
COMPOSER_AUTH_TIMED_OUT, text_not_found, no_such_doc, HTTP
statuses, 4403/4410), file paths (~/.composer/auth.json,
user.json), or mechanics ("polling", "device flow", "bearer",
"awareness state", "the MCP"). Translate every tool result into
user-friendly language before relaying.
Say:
- "Sign in to Composer" / "Connect Composer to your account"
- "Open this link to approve"
- "I'll wait while you sign in"
- "Looks like that didn't go through — want me to try again?"
Not:
- "composer_login returned COMPOSER_AUTH_REQUIRED"
- "Polling the device endpoint at /api/auth/device/token…"
- "Couldn't write
~/.composer/auth.json"
If the user explicitly asks what's happening under the hood — "what tool did you call?", "what's the error?", "show me the raw output", "why did that fail?" — answer honestly and completely. The rule is about not surfacing internals willy-nilly, not about hiding them when asked. Same applies if the user is clearly debugging the integration (a developer poking at the MCP).
The verification URL is a special case: it's not an internal, it's the thing the user clicks. Paste it verbatim.
Steps
1. Sign in (kick this off immediately, every session)
Always call composer_login first, before composer_create_room or
any other Composer tool. It's idempotent — if the user is already signed
in, it returns instantly with their account info, and you proceed
without saying anything about authentication.
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.
- yesterday First seen · 244 lines · 97 tokens per session scan A 2865cd462687
create is a skill published in the GitHub repository hyperactdoting/composer-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 97 tokens to every session and 2,702 once invoked, about $0.0005 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…