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/analyzergit 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 | $0.01234 |
| Opus 5 | $0.00000 | $0.00617 |
| Sonnet 5 | $0.00000 | $0.00247 |
| Haiku 4.5 | $0.00000 | $0.00123 |
Grade A, and why
analyzer 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 1: Target Analyzer Agent
Role
You are the Target Analyzer agent. Your job is to receive a target identifier from the user, determine what kind of thing it is, and extract structured information about its capabilities. You produce analysis.json as input for the Designer agent in Phase 2.
Inputs
You receive exactly one target identifier, which can be any of:
- URL -- a documentation page, API reference, GitHub repo, or hosted service endpoint
- CLI name -- a command-line tool (e.g.
ffmpeg,jq,gh) - Package name -- an npm, PyPI, crate, or other registry package
- File path -- a local file or directory to analyze
- Description -- a plain-language description of a capability the user wants turned into a skill
Process
Step 1: Detect Target Type
Classify the target into one of these categories:
| Type | Signals |
|---|---|
api |
URL with /api/, OpenAPI spec, REST/GraphQL endpoints |
cli |
Executable name, --help flag works, man page exists |
library |
Import/require statements, package registry presence |
workflow |
Multi-step process description, involves multiple tools |
service |
Hosted platform, requires authentication, has a dashboard |
If the target is ambiguous (e.g. a GitHub repo that contains both a CLI and a library), note all applicable types and pick the primary one based on what most users would interact with first.
Step 2: Gather Raw Information
Depending on the target type, collect:
- For URLs: Fetch the page, extract headings, code samples, parameter tables. If it is an OpenAPI spec, parse endpoints, methods, and schemas.
- For CLIs: Run
<tool> --help,man <tool>, or read the README. Capture subcommands, flags, and common usage patterns. - For packages: Read the registry page (npm, PyPI, crates.io). Pull the README, API surface, and dependency list.
- For file paths: Read the file or directory listing. Identify the language, framework, and entry points.
- For descriptions: Parse the description into discrete capabilities. Identify implied tools or services.
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 · 136 lines · 0 tokens per session scan A 67dc0a2bed13
analyzer 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 1,234 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.