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 Momo2323-ui/claude-orchestra --skill skill-selectorgit clone --depth 1 https://github.com/Momo2323-ui/claude-orchestraWrote 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/momo2323-ui/claude-orchestra/skill-selector)<a href="https://agentmods.dev/skills/momo2323-ui/claude-orchestra/skill-selector"><img src="https://agentmods.dev/badge/skills/momo2323-ui/claude-orchestra/skill-selector/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/momo2323-ui/claude-orchestra/skill-selector"><img src="https://agentmods.dev/badge/skills/momo2323-ui/claude-orchestra/skill-selector.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 | $0.00106 | $0.06781 |
| Opus 5 | $0.00053 | $0.03390 |
| Sonnet 5 | $0.00021 | $0.01356 |
| Haiku 4.5 | $0.00011 | $0.00678 |
Grade A, and why
skill-selector 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 12d 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 "https://skills.sh/api/search?q=<query>"` when the interactive CLI can't run). How it starts
The opening of the file, as written. The whole thing — 631 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Selector — Picking Between Similar Skills Within an Orchestra
"An orchestra can hold many skills that do the same job in different ways. Check them all, try them when the task is complex, and ask the human when you're unsure."
This skill operationalizes that into a transparent scoring + announcement + learning loop.
The problem this solves
Most orchestras have multiple candidates for the same task:
| Orchestra | Example overlap |
|---|---|
| DESIGN | frontend-design · ui-ux-pro-max · modern-web-design · web-design-engineer · taste-design · 21st.dev (magic) |
| RESEARCH | search-agent · deep-research · market-research · firecrawl · brightdata-plugin · nimble |
| LEAD GEN | Apollo · Apify · brightdata · search-agent · sales-outreach |
| BUILD | code-reviewer · pr-review-toolkit · superpowers:requesting-code-review |
| CONTENT | content-creator · copywriting · marketing-content-creator · book-co-author |
Picking randomly = inconsistent quality. Picking by recency = staleness. Picking by name = bias.
This skill picks deterministically, explains why, and asks when uncertain.
When to invoke
- Automatically: when more than ONE skill in the active orchestra's roster matches the task signal
- Manually: when the user says "pick the right skill for X" or "which design skill should I use"
- Inside
orchestra-router: as a sub-step after orchestra activation, before player invocation
Skip when: only one skill in the orchestra matches the task (no choice to make), or the user has explicitly named a specific skill ("use ui-ux-pro-max").
The scoring algorithm
For each candidate skill in the target orchestra, compute a score 0–1:
score = (
relevance_to_task * 0.35 # how well the skill description matches the task
+ user_vision_alignment * 0.25 # match against stated vision (e.g. "premium" → max-pro)
+ prior_preference_weight * 0.20 # pulled from ~/.claude/projects/<x>/memory/feedback
+ complexity_fit * 0.15 # task complexity vs skill's complexity-fit field
+ skill_freshness * 0.05 # slight novelty boost for less-used skills
)
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.
- 12d ago First seen · 631 lines · 106 tokens per session scan A 1733b086f611
skill-selector is a skill published in the GitHub repository Momo2323-ui/claude-orchestra (8 stars, last pushed 1mo ago), licensed MIT. It adds 106 tokens to every session and 6,781 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
mle-workflow
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
autonomous-loops
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
react-patterns
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.