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/captainyouz/agentdex/claude-mdgit clone --depth 1 https://github.com/CaptainYouz/agentdexWrote 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/captainyouz/agentdex/claude-md)<a href="https://agentmods.dev/instructions/captainyouz/agentdex/claude-md"><img src="https://agentmods.dev/badge/instructions/captainyouz/agentdex/claude-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 | $0.01484 | $0.01484 |
| Opus 5 | $0.00742 | $0.00742 |
| Sonnet 5 | $0.00297 | $0.00297 |
| Haiku 4.5 | $0.00148 | $0.00148 |
Grade A, and why
agentdex CLAUDE.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 4d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Agentdex
Context for AI assistants working on this repo.
Purpose
Desktop app (Tauri 2) to browse skills, subagents, rules, and context (CLAUDE.md) for Cursor, Claude, and Codex under the home directory (~ / %USERPROFILE%). Users search/filter the catalog, preview and edit files, show paths in the system file manager, and explore the surrounding folder tree.
Platforms: macOS (primary), Windows, Linux (best-effort). Home directory uses dirs::home_dir(). Plugin skill paths use Path::components(), not string splitting.
Commands
pnpm install
pnpm tauri dev # dev app (Vite on :1420 + Rust backend)
pnpm tauri build # production bundle
pnpm build # frontend only (vue-tsc + vite)
pnpm lint # eslint
Do not run tests or tauri dev unless the user asks.
Architecture
src-tauri/src/ Rust backend (filesystem + scan)
lib.rs Tauri commands (IPC entry points)
scanner.rs Catalog scan logic
parser.rs YAML frontmatter for skills/agents
directory.rs Lazy directory listing (worktree panel)
types.rs Serde types (camelCase JSON to frontend)
src/ Vue 3 + TypeScript UI
pages/home/Home.vue Main screen (catalog + detail + worktree)
composables/ useCatalog, useWorktree, useFileActions, …
components/ Presentational UI
types/*.types.ts Frontend types
constants/*.constants.ts
utils/ Pure helpers
Data flow: Home.vue → useCatalog → invoke('scan_catalog') → scanner::build_catalog → grouped CatalogResponse. File ops use read_item_file, write_item_file, delete_item_file, reveal_item_path, get_item_file_stats. Worktree uses get_home_directory + list_directory_children.
When changing catalog shape, update both src-tauri/src/types.rs and src/types/catalog.types.ts (serde rename_all = "camelCase" on Rust side).
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.
- 4d ago First seen · 111 lines · 1,484 tokens per session scan A b87127610183
agentdex CLAUDE.md is an instructions file published in the GitHub repository CaptainYouz/agentdex (7 stars, last pushed 21d ago), licensed MIT. It adds 1,484 tokens to every session, about $0.0074 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
roblox-brain AGENTS.md
AGENTS.md instructions for TabooHarmony/roblox-brain, covering agents.md: guide for ai agents and contributors, what this repo is, architecture: progressive disclosure, skill file structure and skill title.
apple-dev-skills AGENTS.md
AGENTS.md instructions for markdavidgan/apple-dev-skills, covering apple dev skills — agent guide (codex / kimi / cross-cli), quick reference, repository rules, project-local consumer convention and checkpoint compaction protocol.
alphaloop AGENTS.md
Instructions for realnaka/alphaloop, covering alphaloop — agent instructions, what you are looking at, quick install (any agent), how to use as an agent and key files in this repo.
template GEMINI.md
Instructions for ai-plugin-marketplace/template, covering skill evaluator, usage and how it works.
skene-cookbook AGENTS.md
Instructions for SkeneTechnologies/skene-cookbook, covering agents.md, quick context, build & test commands, install dependencies and run tests (full suite).
DSPy-Programming-not-prompting-LMs-skills CLAUDE.md
Claude Code instructions for lebsral/DSPy-Programming-not-prompting-LMs-skills, covering dspy skills repository, conventions, workspace directory, repo structure and adding or updating a skill.