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/llrowat/agent-corral/claude-mdgit clone --depth 1 https://github.com/llrowat/agent-corralWrote 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/llrowat/agent-corral/claude-md)<a href="https://agentmods.dev/instructions/llrowat/agent-corral/claude-md"><img src="https://agentmods.dev/badge/instructions/llrowat/agent-corral/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 | $0.02537 | $0.02537 |
| Opus 5 | $0.01269 | $0.01269 |
| Sonnet 5 | $0.00507 | $0.00507 |
| Haiku 4.5 | $0.00254 | $0.00254 |
Grade A, and why
agent-corral 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentCorral - Claude Code Configuration Manager
Project Structure
This is a Tauri v2 + React (TypeScript) desktop application with a Rust backend. The app focuses on managing Claude Code configuration — agents, hooks, skills, MCP servers, memory, and config export/import — at both global and project scope.
agent-corral/
├── backend/ # Rust backend (Tauri app)
│ ├── src/
│ │ ├── lib.rs # App entry, state management
│ │ ├── main.rs # Binary entry
│ │ ├── preferences.rs # App preferences (plugin sync interval)
│ │ ├── commands/ # Tauri IPC command handlers
│ │ │ ├── claude.rs # Agent CRUD
│ │ │ ├── hooks.rs # Hooks management
│ │ │ ├── mcp.rs # MCP servers
│ │ │ ├── pack.rs # Legacy pack system
│ │ │ ├── plugin.rs # Plugin system + import sync
│ │ │ ├── preferences.rs # App preferences
│ │ │ ├── repo.rs # Repository registry
│ │ │ └── skills.rs # Skills
│ │ ├── repo_registry/ # SQLite repo management
│ │ ├── claude_adapter/ # Claude Code file format adapter (agents, hooks, skills, MCP, memory)
│ │ ├── plugin_manager/ # Plugin export/import/git install/update, import sync registry
│ │ └── pack_manager/ # Legacy pack system (.agentpack JSON, kept for migration)
│ └── tauri.conf.json
├── frontend/ # React frontend
│ ├── components/ # Shared UI components
│ │ ├── Sidebar # Navigation sidebar
│ │ ├── ScopeSwitcher # Global/Project scope selector
│ │ ├── ScopeGuard # Scope protection wrapper
│ │ ├── RepoSwitcher # Repository selection (with file picker dialog)
│ │ ├── ConfigSummary # Configuration overview widget
│ │ ├── DocsLink # Links to Anthropic docs per feature
│ │ ├── InlineValidation # Form validation with auto-fix suggestions
│ │ ├── PresetPicker # Generic preset selection modal
│ │ ├── QuickSetup # First-run setup wizard with starter presets
│ │ ├── CreateWithAiModal # AI-powered entity creation (launches terminal)
│ │ ├── ConfigLinter # Config linting with hierarchy conflict detection
│ │ └── SchemaForm # Generic JSON Schema → form renderer
│ ├── pages/ # Page components
│ │ ├── OverviewPage # Dashboard with config summary
│ │ ├── AgentsPage # Agent studio (create/edit/delete)
│ │ ├── HooksPage # Hooks editor
│ │ ├── SkillsPage # Skills management
│ │ ├── McpPage # MCP servers configuration
│ │ ├── ConfigPage # Settings/configuration editor
│ │ ├── MemoryPage # Memory stores and entries
│ │ ├── PluginsPage # Export/Import UI (config bundles with import sync)
│ │ ├── PacksPage # Legacy pack management
│ │ └── SettingsPage # App preferences (plugin sync interval)
│ ├── hooks/ # React hooks
│ │ ├── useRepos # Repository list
│ │ ├── usePluginSync # Plugin import sync polling
│ │ └── useSchema # JSON Schema loading (local + remote)
│ ├── lib/ # Shared libraries
│ │ ├── tauri # Tauri IPC API bindings
│ │ ├── presets # Built-in presets (agents, hooks, skills, MCP, config, starter presets)
│ │ └── schemas/ # JSON Schemas (official settings + local agent/skill/MCP)
│ ├── types/ # TypeScript type definitions
│ └── styles.css # Global styles (dark theme)
├── .github/workflows/ # CI (test.yml runs Rust + frontend tests)
├── Cargo.toml # Workspace root
├── package.json # Frontend dependencies
└── vite.config.ts # Vite configuration
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 · 159 lines · 2,537 tokens per session scan A 7e1fb53f379e
agent-corral CLAUDE.md is an instructions file published in the GitHub repository llrowat/agent-corral (4 stars, last pushed 5mo ago), licensed MIT. It adds 2,537 tokens to every session, about $0.0127 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
claude-code-profiles CLAUDE.md
Instructions for quinnjr/claude-code-profiles, covering claude.md, project, architecture, command interface and directory-local profiles.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
superpowers-reasonix AGENTS.md
Instructions for christopherarter/superpowers-reasonix, covering project guidance, skills — stop. load a skill before you act, red flags — these thoughts mean stop. you are rationalizing and priority.
ai-mind AGENTS.md
AGENTS.md instructions for HWYD/ai-mind, covering agents, version spec workspace continuity (mandatory), 项目定位, 事实来源优先级 and 开始大改前先读什么.
vvvv-skills CLAUDE.md
Claude Code instructions for tebjan/vvvv-skills, covering vvvv gamma, when to patch vs code, core concepts, live environment and important conventions.
pi AGENTS.md
AGENTS.md instructions for counterposition/pi, covering agents.md, commands, pattern: pnpm --filter @counterposition/pi-web-search run, single test file and single test by name.