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 chinkan/RustFox --skill creating-skillsgit clone --depth 1 https://github.com/chinkan/RustFoxWrote 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/chinkan/rustfox/creating-skills)<a href="https://agentmods.dev/skills/chinkan/rustfox/creating-skills"><img src="https://agentmods.dev/badge/skills/chinkan/rustfox/creating-skills/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/chinkan/rustfox/creating-skills"><img src="https://agentmods.dev/badge/skills/chinkan/rustfox/creating-skills.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 | $0.00036 | $0.01147 |
| Opus 5.5 | $0.00014 | $0.00459 |
| Sonnet 5.5 | $0.00007 | $0.00229 |
| Haiku 4.5 | $0.00004 | $0.00115 |
Grade A, and why
creating-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 13d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating Skills
Writes high-performance, token-efficient skill directories in skills/ and activates them immediately without restarting the bot.
Process
1. Gather Requirements
Ask the user (one question at a time if unclear):
- Name: Slug — lowercase, numbers, hyphens only, e.g.
processing-reports - Trigger: When should this activate? (→
description, and optionally a shorttrigger:catalog line) - Behavior: What should the agent do step-by-step?
- Files: Heavy reference content? Templates? Scripts?
2. Select Archetype
Pick the right pattern from templates.md:
| Archetype | When | SKILL.md budget |
|---|---|---|
workflow |
Step-by-step procedures | < 150 lines |
reference-heavy |
Lookup tables, schemas, large specs | < 80 lines + reference.md |
tool-wrapper |
Wraps specific tools with usage guidance | < 100 lines |
persona |
Role-play or communication style shifts | < 60 lines |
3. Design the Structure
skills/<name>/
├── SKILL.md # Always: main entry point (keep within archetype budget)
├── reference.md # When: heavy content that would exceed budget
├── examples.md # When: input/output examples help significantly
└── scripts/ # Rarely: utility scripts
└── helper.py
Rules:
- References are one level deep only — no chained references
- Split only when SKILL.md exceeds archetype budget
- Every line earns its token cost — cut ruthlessly
4. Write SKILL.md
Required format:
---
name: skill-name-with-hyphens
description: Use when [triggering conditions only — third person, no workflow summary, max 1024 chars]
tags: [optional]
---
# Skill Title
One sentence overview.
## When to Use
- Concrete trigger phrase 1
- Concrete trigger phrase 2
## [Core Section]
Imperative instructions. No fluff.
## Supporting Files
**Topic**: See [reference.md](reference.md)
Frontmatter rules:
name: lowercase, numbers, hyphens; max 64 chars; avoid "anthropic" / "claude"description: "Use when..."; triggers only; no how/what summary; third person; max 1024 chars. Stored in full (the portal reads this). The system prompt does not paste it whole.trigger(optional, single line): the# Available Skillscatalog blurb, at most 24 UTF-8 bytes. When set, that line is the name plus this blurb plus oneLoad with: read_skill_file(skill_name="…", relative_path="SKILL.md"). When omitted,descriptionis truncated to that same cap for the catalog only. If the text already containsLoad with:, a second one is not added.- A bad description causes the agent to skip reading the body — be precise about triggers
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago Changed · +2 lines f7ba6837f1ff
- 2mo ago First seen · 140 lines · 36 tokens per session scan A 18894ea290b0
creating-skills is a skill published in the GitHub repository chinkan/RustFox (12 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 1,147 once invoked, about $0.0001 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 2026-08-31.
creating-skills compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| creating-skillschinkan/RustFox | Skill | 12 | today | MIT | A | 36 | Claude Code, Codex |
| skill-finderellmos-ai/skills | Skill | 9 | yesterday | MIT | A | 118 | Claude Code, Codex |
| skill-register-careellmos-ai/skills | Skill | 9 | yesterday | MIT | A | 117 | Claude Code, Codex |
| skill-family-careellmos-ai/skills | Skill | 9 | yesterday | MIT | A | 104 | Claude Code, Codex |
| pdfjjyaoao/HelloAgents | Skill | 3.4k | 1mo ago | none | A | 51 | Claude Code, Codex |
| Video Generationjjyaoao/HelloAgents | Skill | 3.4k | 1mo ago | none | A | 58 | Claude Code, Codex |
| LLMjjyaoao/HelloAgents | Skill | 3.4k | 1mo ago | none | A | 59 | Claude Code, Codex |