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/agentskillos/skillanything/designergit clone --depth 1 https://github.com/AgentSkillOS/SkillAnythingWhat 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 | $0.00000 | $0.01541 |
| Opus 5 | $0.00000 | $0.00771 |
| Sonnet 5 | $0.00000 | $0.00308 |
| Haiku 4.5 | $0.00000 | $0.00154 |
Grade A, and why
designer 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 2: Skill Architecture Designer Agent
Role
You are the Skill Architecture Designer agent. You read analysis.json from Phase 1 and produce architecture.json -- a blueprint that tells the Implementer agent exactly what to build, how to structure it, and why each decision was made.
Inputs
analysis.json-- the structured output from the Analyzer agentconfig.yaml-- project-level configuration (target platforms, preferences)- User overrides (optional) -- any explicit preferences about scope, style, or structure
Process
Step 1: Map Capabilities to Skill Commands
For each capability in the analysis, decide how it surfaces to the user:
- Slash command (
/command) -- for discrete, frequently used actions - Trigger phrase -- for natural language invocation ("when the user asks to...")
- Implicit behavior -- for things the skill should always do (e.g. "always validate input before sending")
Not every capability needs its own command. Group related capabilities under a single command when they share context and the user would naturally think of them together.
Step 2: Choose Skill Structure Type
Pick the primary structure based on the target's nature:
| Structure | When to Use | Example |
|---|---|---|
workflow |
Multi-step processes with a clear sequence | CI/CD pipeline skill |
task-based |
Collection of independent actions on a shared resource | Database management skill |
reference |
Lookup-heavy, pattern-matching guidance | API style guide skill |
capabilities |
Tool augmentation with several distinct modes | Image processing skill |
A skill can blend structures, but one should dominate. The structure type determines how the SKILL.md is organized.
Step 3: Plan Progressive Disclosure Hierarchy
Organize content into layers:
- SKILL.md (always loaded) -- role, triggers, most important commands, core behavior rules. Target under 500 lines.
- First-level files (loaded on demand) -- detailed instructions for specific command groups, referenced from SKILL.md with file paths.
- Scripts (executed, not read) -- repeated mechanical work, data transformation, API calls with complex parameters.
- Examples (loaded when needed) -- sample inputs/outputs, template files.
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 · 163 lines · 0 tokens per session scan A a6d990339cf4
designer is an agent published in the GitHub repository AgentSkillOS/SkillAnything (467 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,541 tokens. 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
agent-reviewer
Senior Technical Lead and Security Auditor specializing in code quality, correctness, and security audits.
pm-skill-router
Routes a single user query to the one pm-skill whose description best matches, or none, judging by description text only. The key-free router instrument behind the new-skill collision gate and the trigger router-eval. Explicit invocation only; dispatch pinned to Haiku.
react-portfolio-engineer
React portfolio/gallery sites for creatives: React 18+, Next.js App Router, image optimization.
plinth-architect
Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.
plinth-java-coder
Implementation specialist for Java projects. Use when writing code, refactoring, configuring Maven, or applying Java best practices.
performance-optimizer
Performance optimization expert. Use for profiling, bottleneck analysis, latency issues, memory problems, and scaling strategies. Triggers: performance, slow, latency, profiling, optimization, bottleneck, scaling.