skills

A command for finding and activating relevant coding skills from a large skills library. It examines the project and the request to identify useful guidance.

In plain words
What is it for?
Use it at the start of a task involving languages, frameworks, databases, testing, infrastructure, machine learning, frontend work, or workflow tools.
Why use it?
It reduces the work of manually choosing which skills apply to a project. It can use files, technologies, and conversation context to narrow the search.

Command

Install

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.

agentmods
npx agentmods add commands/rand/cc-polymath/skills
Clone the repo
git clone --depth 1 https://github.com/rand/cc-polymath
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,685 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00014 $0.02685
Opus 5 $0.00007 $0.01342
Sonnet 5 $0.00003 $0.00537
Haiku 4.5 $0.00001 $0.00268

Measured 2d ago against content hash 62e92ffcdd9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skills 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 2d 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.

commands/skills.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skills Discovery Assistant

You are helping the user discover and activate relevant skills from their skills library.

Your Task

User's Request: $ARGUMENTS

Follow these steps:

1. Read Skills Catalog

Read the master catalog: Read ../skills/README.md

2. Detect Project Context

Analyze the current directory to understand the project:

# List files to detect project type
ls -la | head -30

# Check for language/framework indicators
ls *.{json,md,go,py,rs,swift,zig,toml,yaml,yml} 2>/dev/null | head -20

Technology Detection → Gateway Mapping:

  • package.jsondiscover-frontend (React, Next.js, TypeScript)
  • go.moddiscover-api (Go), discover-infra
  • requirements.txt, pyproject.toml, uv.lockdiscover-api (Python), discover-ml if ML work
  • Cargo.tomldiscover-wasm if WASM, discover-api for web services
  • build.zigdiscover-zig
  • *.swift, *.xcodeprojdiscover-mobile (iOS/Swift)
  • Dockerfile, docker-compose.ymldiscover-infra
  • .beads/ → Beads workflow skills (root level)
  • tests/, __tests__/discover-testing
  • Database files → discover-database

3. Analyze Conversation Context

Review the current conversation for:

  • Technologies mentioned (frameworks, tools, databases)
  • Problems discussed (performance, debugging, deployment)
  • Explicit skill requests
  • Work phase (planning, implementation, testing, deployment)

Map to gateway keywords:

  • "REST API" → discover-api
  • "GraphQL" → discover-api
  • "Postgres", "MongoDB", "Redis" → discover-database
  • "Docker", "Kubernetes", "Terraform", "AWS", "GCP" → discover-infra
  • "CI/CD", "GitHub Actions", "Make", "CMake", "Bazel" → discover-cicd
  • "TCP", "HTTP/2", "gRPC", "Nginx", "proxy" → discover-networking
  • "debugging", "GDB", "profiling", "logging", "metrics" → discover-debugging
  • "caching", "CDN", "Redis cache" → discover-database
  • "ML", "model", "training", "Modal" → discover-ml
  • "math", "linear algebra" → discover-math
  • "compiler", "parser", "AST", "eBPF", "Z3", "Lean" → discover-systems-theory
  • "diagram", "flowchart", "Mermaid" → discover-engineering
  • "MCP", "MCP server", "tool protocol" → discover-mcp
  • "agent", "agentic", "tool use", "task decomposition" → discover-agentic
  • "WebSocket", "SSE", "CRDT", "consensus" → discover-distributed
  • "product", "roadmap", "collaboration", "GitHub workflows" → discover-product

Read the full file on GitHub · 327 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. 2d ago First seen · 327 lines · 0 tokens per session scan A 62e92ffcdd9c

Subscribe to this mod's changes

skills is a command published in the GitHub repository rand/cc-polymath (135 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 2,685 once invoked, about $0.0001 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.