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-creatorgit 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 | $0.00042 | $0.00696 |
| Opus 5 | $0.00021 | $0.00348 |
| Sonnet 5 | $0.00008 | $0.00139 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
skill-creator 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator
Generate new skills for the cc-polymath library that follow the Agent Skills spec and cc-polymath conventions.
Process
1. Understand the Request
- What domain/topic does the skill cover?
- Is this a gateway skill, INDEX, or leaf skill?
- Which existing category does it belong to (or is it a new category)?
2. Check Existing Skills
- Read
skills/README.mdfor the master catalog - Check if a similar skill already exists using Grep
- Identify the target category directory
3. Generate the Skill
For leaf skills (skills/{category}/{name}.md):
---
name: {category}-{skill-name}
description: One-line description of the skill (up to 1024 chars)
---
Body structure:
# {Title}— clear, descriptive**Scope**: .../**Lines**: ~N## When to Use This Skill— bullet list of triggers## Core Concepts— organized subsections with code examples## Anti-Patterns— common mistakes with corrections## Checklist— quick reference for applying the skill## Related Skills— cross-references using../skills/...
For gateway skills (skills/discover-{category}/SKILL.md):
---
name: discover-{category}
description: Automatically discover {category} skills when working with {keywords}. Activates for {domain} tasks.
license: MIT
metadata:
author: rand
version: "3.1"
compatibility: Designed for Claude Code. Compatible with any agent supporting the Agent Skills format.
---
Body structure:
- Title, description
- When This Skill Activates (bullet list)
- Available Skills (numbered quick reference)
- Load commands using
Read ../skills/... - Common Workflows (sequences of skills)
- Progressive Loading section
For INDEX.md (skills/{category}/INDEX.md):
- Category Overview (Total Skills, Focus, Use Cases)
- Each skill: Description, Lines, Use When (bullets), Key Concepts
- Common Workflows with sequences
- Skill Combinations with other categories
4. Quality Checks
- Name is kebab-case, 1-64 characters
- Description ≤ 1024 characters
- Leaf skills: 200-400 lines, focused on one topic
- Code examples are practical and correct
- Cross-references use
..prefix - No overlap with existing 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.
- 2d ago First seen · 84 lines · 42 tokens per session scan A dab5a1f057eb
skill-creator is an agent published in the GitHub repository rand/cc-polymath (135 stars, last pushed 6mo ago), licensed MIT. It adds 42 tokens to every session and 696 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
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
declarative
Learn how to define agents declaratively using configuration files in Agent Framework.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
claude-agent-helper
A Claude Code subagent. OpenCode does not read Claude agents.
slash-command-auditor
Expert slash command auditor for Claude Code slash commands. Use when auditing, reviewing, or evaluating slash command .md files for best practices compliance. MUST BE USED when user asks to audit a slash command.