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 skills add frankxai/claude-skills-library --skill sigit clone --depth 1 https://github.com/frankxai/claude-skills-libraryWrote 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.
[](https://agentmods.dev/skills/frankxai/claude-skills-library/si)<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/si"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/si/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.
<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/si"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/si.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00073 | $0.00722 |
| Opus 5.5 | $0.00029 | $0.00289 |
| Sonnet 5.5 | $0.00015 | $0.00144 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
si 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 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.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/si — Superintelligence Router
Route ANY ask through this 3-step protocol:
Step 1 — Classify intent
Parse $ARGUMENTS for verb. Match against these classes:
Execution verbs (route to: reasoning + swarm)
build, ship, deploy, fix, elevate, create, refactor, migrate, scaffold, wire, sync, audit-and-fix, redesign, rebuild, generate, render
Reasoning verbs (route to: reasoning only)
think, plan, compare, analyze, should, what if, why, evaluate, audit, research, explore, decide
Bare topic (no verb)
Route to: reasoning only, then ASK "Should I dispatch a swarm to execute this?"
Step 2 — Invoke /superintelligence
Always. Pass $ARGUMENTS as the topic. Capture the reasoning output.
Cost: ~5K input + ~3K output tokens, ~$0.05. Cheap enough to always run.
Step 3 — Route based on Step 1 classification
If execution intent
After /superintelligence returns, dispatch the appropriate swarm:
- "build / scaffold / create / generate" → BUILD lane (e.g., /v BUILD or feature-dev or frankx-website-builder agent)
- "deploy / ship / sync" → DEPLOY lane (e.g., /v DEPLOY)
- "fix / refactor / migrate" → FIX lane
- "elevate / redesign / rebuild" → ELEVATE lane (e.g., /v ELEVATE)
- "audit-and-fix" → /v ELEVATE
- Multi-domain ambiguity → ask which lane
If reasoning intent
Return /superintelligence verdict directly. Surface a one-line "Want to execute this?" footer.
If bare topic
Return /superintelligence verdict. Surface explicit "Should I dispatch a swarm to execute this?" question with 3 options (yes-execute / no-thinking-only / scope-first).
Cost discipline
- Never auto-dispatch a swarm on a bare-topic ask
- Never skip /superintelligence on execution intent (the framing is the value)
- Per-invocation cost budget:
$0.05 reasoning + variable swarm cost ($0.30-$3 per agent × N agents) - Compare to: a pure /v ELEVATE run is ~$1.50-$5 — /si adds $0.05 of reasoning at the front for better orchestration
Anti-patterns
- Auto-dispatching swarm on every /si call (burns money on tasks that needed only thinking)
- Skipping /superintelligence on execution (loses multi-perspective framing)
- Treating /si as an alias for /superintelligence (it's a router, not a duplicate)
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.
- 1mo ago First seen · 66 lines · 73 tokens per session scan A 5c8b5f786329
si is a skill published in the GitHub repository frankxai/claude-skills-library (47 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 722 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 2026-09-03.
Other skills, from other repositories
token-saver
Token optimization guide for Claude Code. This skill should be used when the user wants to reduce API costs, learn model routing strategies, or understand how to use free/cheaper tools (Ollama, Haiku) instead of burning expensive Claude tokens on routine tasks. Triggers on: save tokens, reduce costs, token tips, cheap…
wayfinder
A planning method that maps a large, uncertain project into linked decision tickets in a repository's issue tracker. An issue tracker is a system for recording and organizing project work.
scaffold-exercises
A directory scaffold for course exercises, with sections, exercise folders, and optional problem, solution, or explanation versions. It creates the required Markdown files and checks the result with the repository's linter.
domain-modeling
A practice for building and maintaining a project’s domain model: the shared terms, concrete scenarios, and recorded architecture decisions that describe what the software is about.
migrate-to-shoehorn
A testing guide for Shoehorn, a TypeScript library that lets tests provide only the fields they need from a larger data type.
ask-matt
A skill router that helps choose the right workflow or skill for the current task. It maps work from an initial idea through building and shipping, with separate paths for research, prototypes, and multi-session projects.