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/ironystock/agentic-obs/claude-mdgit clone --depth 1 https://github.com/ironystock/agentic-obsWrote 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/ironystock/agentic-obs/claude-md)<a href="https://agentmods.dev/instructions/ironystock/agentic-obs/claude-md"><img src="https://agentmods.dev/badge/instructions/ironystock/agentic-obs/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 5.1 | $0.01989 | $0.01989 |
| Opus 5 | $0.00994 | $0.00994 |
| Sonnet 5 | $0.00398 | $0.00398 |
| Haiku 4.5 | $0.00199 | $0.00199 |
Grade A, and why
agentic-obs 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 6d 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.MD
Context for AI assistants working on the agentic-obs project.
Project Overview
agentic-obs is an MCP (Model Context Protocol) server providing AI assistants with programmatic control over OBS Studio via the WebSocket API.
Current Status: 81 Tools | 4 Resources | 14 Prompts | 4 Skills
Project Structure
agentic-obs/
├── main.go # Entry point (MCP server or TUI dashboard)
├── config/config.go # Configuration management
├── internal/
│ ├── mcp/
│ │ ├── server.go # MCP server lifecycle
│ │ ├── tools.go # Tool registration (81 tools)
│ │ ├── resources.go # Resource handlers (4 types)
│ │ ├── prompts.go # Prompt definitions (14 prompts)
│ │ ├── completions.go # Autocomplete handler
│ │ ├── elicitation.go # User confirmation for high-risk tools
│ │ ├── help.go # Help tool
│ │ └── interfaces.go # OBSClient interface
│ ├── obs/
│ │ ├── client.go # WebSocket client
│ │ ├── commands.go # OBS command implementations
│ │ └── events.go # Event handling
│ ├── docs/ # Embedded documentation (go:embed)
│ ├── storage/ # SQLite persistence
│ ├── http/ # Web dashboard & API (/docs/ endpoints)
│ ├── screenshot/ # Background capture
│ └── tui/ # Terminal dashboard (4 views)
├── skills/ # Claude Skills (4 packages)
├── examples/ # Usage examples
├── docs/ # Additional documentation
└── design/ # Architecture & decisions
Key Technologies
| Component | Package | Version |
|---|---|---|
| MCP SDK | github.com/modelcontextprotocol/go-sdk |
1.1.0 |
| OBS Client | github.com/andreykaipov/goobs |
1.5.6 |
| SQLite | modernc.org/sqlite |
latest |
| TUI | github.com/charmbracelet/bubbletea |
1.3.3 |
| Markdown (HTML) | github.com/yuin/goldmark |
1.7.x |
| Markdown (Terminal) | github.com/charmbracelet/glamour |
0.8.x |
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.
- 6d ago First seen · 225 lines · 1,989 tokens per session scan A 4c89abd536f5
agentic-obs CLAUDE.md is an instructions file published in the GitHub repository ironystock/agentic-obs (31 stars, last pushed 4mo ago), licensed MIT. It adds 1,989 tokens to every session, about $0.0099 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 2026-08-30.
Other instructions, from other repositories
wanaku CLAUDE.md
Claude Code instructions for wanaku-ai/wanaku, covering wanaku, core guidelines, quick start, build info and architecture.
wanaku AGENTS.md
AGENTS.md instructions for wanaku-ai/wanaku, a project described as: Wanaku MCP Router.
autogen copilot-instructions.md
Copilot instructions for microsoft/autogen, covering autogen multi-agent ai framework, working effectively, prerequisites and environment setup, python development workflow and quick validation (under 1 second each).
hatch3r CLAUDE.md
Claude Code instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).
blz AGENTS.md
Instructions for outfitter-dev/blz, covering blz repository instructions for ai agents, important, working memory, use blz and 🚀 quick start for agents.
htmldrop AGENTS.md
Instructions for vin-spiegel/htmldrop, covering htmldrop — mcp server for publishing html, service endpoints, connect as an mcp client, available tool and publishhtml.