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 instructions/okhp3/skillz/agents-mdgit clone --depth 1 https://github.com/OKHP3/skillzWhat 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 | $0.08039 | $0.08039 |
| Opus 5 | $0.04019 | $0.04019 |
| Sonnet 5 | $0.01608 | $0.01608 |
| Haiku 4.5 | $0.00804 | $0.00804 |
Grade A, and why
skillz AGENTS.md 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 — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md: OKHP3/skillz
This is the canonical agent guide and routing index for this repository. Read it before working here. CLAUDE.md is a compatibility pointer to this file.
Project identity
- Suite: OverKill Hill
- Repository:
OKHP3/skillz - Type: Public Agent Skills distribution library, using the
SKILL.mdformat - License: MIT at the repository level; individual skills may declare a different license in frontmatter
- Release state: Unreleased. There are no Git tags.
- Current inventory: 283 distribution skills in 19 active families, and 46 project-local support skills under
.agents/skills/ - Source of truth: GitHub repository for installable files; the public landing surface is OverKill Hill
/projects/skillz/
Mission: confirmed
Package recurring methods as portable, agent-readable delegation contracts that can run across compatible agent runtimes without repeating the same human explanation.
Vision: inferred
Become the reusable execution layer of the OKHP3 Visual Language Stack, with composable skill families that make recurring work portable and durable.
Scope and boundaries
This repository contains SKILL.md contracts, references, examples, fixtures, and small validation or rendering utilities. It also contains the artifacts/forge/ Vite/React frontend that builds the public Skillz Forge catalog, alongside the Review Desk, API server, and Mockup Sandbox artifacts. It is a pnpm workspace; use the artifact and package-local commands documented below. There is one Git repository at the root; no nested Git repositories were found.
The root family directories are the distribution surface. .agents/skills/ is a project-local support surface containing cataloging, skill-authoring, FoundRy tooling, and platform-specific context-extraction support. Do not count its packages as additional distribution skills or families.
Do not add employer-specific confidential material, private credentials, tokens, cookies, customer or employee data, proprietary system names, hidden network calls, or destructive behavior. Public skills must use synthetic or public-safe examples. A skill must not instruct an agent to bypass permissions, conceal actions, or remove user consent.
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 · 378 lines · 8,039 tokens per session scan A ba4f6d064033
skillz AGENTS.md is an instructions file published in the GitHub repository OKHP3/skillz (2 stars, last pushed 2d ago), licensed MIT. It adds 8,039 tokens to every session, about $0.0402 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 2026-08-31.
Other instructions, from other repositories
vast-cli CLAUDE.md
Instructions for vast-ai/vast-cli, covering vast-ai/vast-cli and ai agents.
mcp-ai-agent-guidelines copilot-instructions.md
Instructions for Anselmoo/mcp-ai-agent-guidelines, covering mcp-ai-agent-guidelines, build, test, and lint, high-level architecture and key conventions.
skill-validator CLAUDE.md
Instructions for raphaelstolt/skill-validator, covering skill-validator, project info, common commands, code conventions and architecture.
bdb-dev-optimized-agent-skills CLAUDE.md
Instructions for hybridlabor-api/bdb-dev-optimized-agent-skills, covering bdb agent skills — global instructions, docs & pipeline, how many agents, safety gate — mechanically enforced, not advisory and non-negotiable.
ai-article-factory GEMINI.md
Instructions for weitzu-com/ai-article-factory, a project described as: AI Article Factory — a Claude Code skill that turns any material/topic/product into illustrated, SEO+GEO-optimized articles in Markdown + Word, plus website/LinkedIn/X copy. Automated end-to-end; human only reviews & publishes.
iago CLAUDE.md
Instructions for drakulavich/iago, covering claude.md, project overview, critical rules (read before changing anything), install & invoke and claude code (plugin).