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/dannykkh/skill-olympus/agents-mdgit clone --depth 1 https://github.com/Dannykkh/skill-olympusWrote 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/instructions/dannykkh/skill-olympus/agents-md)<a href="https://agentmods.dev/instructions/dannykkh/skill-olympus/agents-md"><img src="https://agentmods.dev/badge/instructions/dannykkh/skill-olympus/agents-md.svg" alt="Measured on agentmods" 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 | $0.08299 | $0.08299 |
| Opus 5 | $0.04150 | $0.04150 |
| Sonnet 5 | $0.01660 | $0.01660 |
| Haiku 4.5 | $0.00830 | $0.00830 |
Grade B, and why
skill-olympus AGENTS.md scanned grade B with 1 finding 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 today.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.gemini/config/`, and `agy` as the executable. How it starts
The opening of the file, as written. The whole thing — 452 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI coding agents (Claude Code, Cursor, Copilot, etc.) when working with code in this repository.
[Docs Index]|root: ./
|IMPORTANT: Prefer retrieval-led reasoning over pre-training knowledge |skills/:{ai-tools,meta,documentation,frontend,development,planning,professional,testing,git,utilities} |agents/:{fullstack,ai-ml,api,qa,docs,design,migration,planning,communication,general}
Quick Retrieval Paths
| Task | Read First |
|---|---|
| AI/LLM API 코딩 | 프로젝트 SDK·lockfile·기존 추상화·평가 테스트 우선; 공급자 공식 문서 확인, OpenAI는 openai-docs 사용 |
| React/Next.js | 프로젝트 manifest·lockfile·tsconfig·기존 구조·테스트 우선; 버전 API는 공식 문서 확인 |
| Code Review | skills/code-reviewer/SKILL.md |
| Docker Deploy | skills/docker-deploy/SKILL.md,skills/docker-deploy/templates/ |
| Docker DB Backup | skills/docker-db-backup/SKILL.md |
| API Testing | skills/api-tester/SKILL.md |
| Documentation | 네이티브 작성 + 목적별 skills/api-handoff, documentation-and-adrs, release-notes, crafting-effective-readmes |
| FastAPI | 프로젝트·공식 문서 우선; 명시 요청 시 skills/python-backend-fastapi/SKILL.md |
| Spring Boot | 프로젝트 build manifest·BOM·기존 계층·설정·테스트 우선; 버전 API는 공식 문서 확인 |
| ASP.NET Core | 프로젝트·공식 문서 우선; agents/backend-dotnet.md는 소스 참고용 |
| WPF Desktop | 프로젝트·공식 문서 우선; agents/desktop-wpf.md는 소스 참고용 |
| Database Design | skills/database-schema-designer/SKILL.md |
| Database (MySQL) | 프로젝트 DB 버전·schema·migration 도구·실행 계획 우선 |
| Database (PostgreSQL/Supabase) | 프로젝트 schema·RLS·연결 설정 우선; 명시 요청 시 skills/supabase-postgres-best-practices/SKILL.md |
| Migration | 네이티브 코드 탐색 후 skills/deprecation-and-migration/SKILL.md |
| Naming | 명시 요청 시 skills/naming-analyzer/SKILL.md |
| Architecture | 네이티브 계획·검토 + skills/documentation-and-adrs/SKILL.md; 필요 시 mermaid-diagrams |
| SPEC Interview | skills/zephermine/SKILL.md |
| Security Review | skills/code-reviewer/SKILL.md,skills/code-reviewer/references/security-audit.md |
| Web Preview + 디자인 토큰 | DESIGN.md 우선; 명시 요청 시 skills/design-system-starter/SKILL.md |
| Stitch UI | skills/stitch/SKILL.md |
| Agent Teams (4-CLI 네이티브 병렬 실행) | skills/agent-team/SKILL.md |
| Codex Multi-Agent Team | skills/agent-team-codex/SKILL.md |
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.
- today Changed · +65 lines · +1,112 tokens per session scan A → B 971fb7c8622d
- 4d ago First seen · 387 lines · 7,187 tokens per session scan A ab9108f878df
skill-olympus AGENTS.md is an instructions file published in the GitHub repository Dannykkh/skill-olympus (5 stars, last pushed 2d ago), licensed MIT. It adds 8,299 tokens to every session, about $0.0415 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
babysitter CLAUDE.md
Claude Code instructions for a5c-ai/babysitter, covering claude.md, repo-specific overrides, read these first, quick commands and claude code local notes.
claude-code-second-brain AGENTS.md
Instructions for shofer-dev/claude-code-second-brain, covering agents.md, read first, invariants and working here.
loadout CLAUDE.md
Instructions for AmElmo/loadout, covering loadout, project structure, tech stack, key commands and test fixtures.
Warden-AI GEMINI.md
Gemini CLI instructions for rynald0cst0ltziam/Warden-AI, covering warden — context governance and verification layer, session start (important — do this first), layer 1: before starting work — context selection, layer 2: during work — tool output pruning and enforcement hooks (automatic).
TideCode AGENTS.md
AGENTS.md instructions for ceciliomichael/TideCode, covering tideflow, core rule, workflow, 1. explore first and 2. plan with the user.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).