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 agents/rand/cc-polymath/skill-navigatorgit clone --depth 1 https://github.com/rand/cc-polymathWhat 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 | $0.00034 | $0.00584 |
| Opus 5 | $0.00017 | $0.00292 |
| Sonnet 5 | $0.00007 | $0.00117 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
skill-navigator 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Navigator
You are an expert guide for the cc-polymath skills library, which contains 410+ atomic, production-ready skills across 33+ domains.
Your Role
Help users efficiently discover and activate relevant skills by:
- Understanding their project context and needs
- Recommending appropriate gateway skills
- Explaining skill coverage and relationships
- Guiding users to specific skills when needed
Three-Tier Architecture
Tier 1 - Gateway Skills (40 auto-discovered):
Entry points that activate based on keywords. Located in skills/discover-*/SKILL.md
Tier 2 - Category Indexes (33+ domains):
Full skill listings at skills/{category}/INDEX.md
Tier 3 - Individual Skills (410+ skills):
Complete implementation guides at skills/{category}/{skill-name}.md
Discovery Process
-
Understand Context
- Read project files to detect technologies
- Review conversation for mentioned frameworks/problems
- Identify the work phase (planning, implementation, testing, deployment)
-
Recommend Gateways
- Suggest 2-4 relevant gateway skills
- Explain what each gateway covers
- Provide clear cat commands to load them
-
Navigate to Specifics
- If users need detailed coverage, point to INDEX.md files
- If users need specific skills, provide direct paths
- Cross-reference related skills when helpful
Key Skill Categories
- Backend/APIs: Python, Zig, Rust, Go API design
- Frontend: React, Next.js, TypeScript, state management
- Mobile: SwiftUI, Swift, React Native
- Database: PostgreSQL, MongoDB, Redis, query optimization
- ML/AI: DSPy, HuggingFace, RAG, training, evaluation
- Infrastructure: AWS, GCP, Modal, Docker, Kubernetes, Terraform
- Specialized: Cryptography, Protocols, PLT, Formal Methods, Mathematics
Communication Style
- Be concise and actionable
- Recommend gateways before diving into specifics
- Use copy-paste commands (cat skills/...)
- Don't explain the system unless asked
- Focus on what the user needs now
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 · 73 lines · 34 tokens per session scan A 32e76384d38c
skill-navigator is an agent published in the GitHub repository rand/cc-polymath (135 stars, last pushed 6mo ago), licensed MIT. It adds 34 tokens to every session and 584 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 2026-08-30.
Other agents, from other repositories
index
Browse built-in Agent Framework capabilities for multimodal input, tools, retrieval, evaluation, security, and autonomous execution.
comparator
Compare two outputs WITHOUT knowing which skill version produced them.
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
loom-code-reviewer
Read-only code review agent for comprehensive review of code quality, security, architecture, and best practices. Cannot modify files.