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/modelcontextprotocol/inspector/agents-mdgit clone --depth 1 https://github.com/modelcontextprotocol/inspectorWhat 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 | $0.40129 | $0.40129 |
| Opus 5 | $0.20064 | $0.20064 |
| Sonnet 5 | $0.08026 | $0.08026 |
| Haiku 4.5 | $0.04013 | $0.04013 |
Grade D, and why
inspector AGENTS.md scanned grade D with 2 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 yesterday.
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 MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
**Every web smoke runs against a throwaway catalog (#1977).** The helper mints a temp dir per run and passes it as `MCP_CATALOG_PATH`; without it the web backend falls back to the developer's real `~/.mcp-inspector/mcp.j Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
│ # same failure class. So `rm -rf test-servers/build` The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- yesterday First seen · 1,066 lines · 40,129 tokens per session scan D 419ff8cf9e1e
inspector AGENTS.md is an instructions file published in the GitHub repository modelcontextprotocol/inspector (10,789 stars, last pushed 2d ago), with no licence file. It adds 40,129 tokens to every session, about $0.2006 per session on Opus 5. A static security scan graded it D with 2 findings (reads mcp configuration, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
CodeWhale CLAUDE.md
Instructions for Hmbown/CodeWhale, a project described as: Open-source coding agent for your terminal, built in Rust and on a journey of continuous community improvement. Issues and PRs welcome.
opentui AGENTS.md
Instructions for anomalyco/opentui, covering opentui agent guide, engineering, tooling and runtimes, verification and portable ffi.
dev3000 AGENTS.md
Instructions for vercel-labs/dev3000, covering agents.md, runtime, local ui, production workflows, browser tools and development rules.
cs CLAUDE.md
Instructions for boyter/cs, covering claude.md, project overview, build & test commands, architecture and query pipeline (pkg/search/).
terminal-browser AGENTS.md
Instructions for zenbu-labs/terminal-browser, a project described as: A browser inside your terminal.
OpenGeometry AGENTS.md
Instructions for OpenGeometry-io/OpenGeometry, covering agents.md, 1. project identity, 2. architecture, runtime flow and build pipeline.