Borrowing it
Nothing to install: this file belongs to charliemtnez/ghost-inspector-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/charliemtnez/ghost-inspector-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/charliemtnez/ghost-inspector-mcpWrote 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/charliemtnez/ghost-inspector-mcp/claude-md)<a href="https://agentmods.dev/instructions/charliemtnez/ghost-inspector-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/charliemtnez/ghost-inspector-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/charliemtnez/ghost-inspector-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/charliemtnez/ghost-inspector-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.07781 | $0.07781 |
| Opus 5 | $0.03890 | $0.03890 |
| Sonnet 5 | $0.01556 | $0.01556 |
| Haiku 4.5 | $0.00778 | $0.00778 |
Grade A, and why
ghost-inspector-mcp CLAUDE.md scanned grade A 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
A 1:1 wrapper does not beat `curl`. The value of this server is in three things: **aggregations the API does not provide**, **guardrails on the write path**, and **tool descriptions that teach the calling model how not t How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ghost-inspector-mcp
MCP server for the Ghost Inspector REST API. Lets any MCP-capable agent (Claude, OpenAI, OpenCode, automations) analyze, validate and safely update end-to-end browser tests without using the Ghost Inspector web UI.
This is a standalone, vendor-neutral tool. It is not part of, and must not depend on, any consumer's project.
What this is / is NOT
| Is | Is NOT |
|---|---|
| A thin, safe wrapper over the GI REST API | A 1:1 mirror of every endpoint |
| A place where hard-won GI gotchas live as executable guardrails | A dumping ground for one company's workflow |
| Read-first, write-with-guards | A destructive admin console |
A 1:1 wrapper does not beat curl. The value of this server is in three things: aggregations the API does not provide, guardrails on the write path, and tool descriptions that teach the calling model how not to break things.
🔴 Non-negotiable: no consumer data in this repo
This repo is private only until the first release, and is written as though it were already public. Hold that line from the first commit: flipping private → public is one click, and it publishes the entire history at once. Nothing organization-specific ever gets committed — not in code, not in tests, not in docs, not in examples. A leak scrubbed in a later commit is still in the history.
Never commit:
- Organization / folder / suite / test IDs
- Folder or suite naming conventions of any specific account
- Test-data identities (names, emails, phone numbers used to fill forms)
- Target hostnames, staging URLs, or environment names
- Any credential, in any form — including truncated values or hashes
All of the above belongs to the consumer's configuration, passed via environment variables or tool arguments at call time. If you find yourself typing a hex ID into a source file, stop.
Use obviously fake placeholders in examples: https://example.com, Jane Tester, [email protected].
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.
- 11d ago First seen · 239 lines · 7,781 tokens per session scan A 002755948d2b
ghost-inspector-mcp CLAUDE.md is an instructions file published in the GitHub repository charliemtnez/ghost-inspector-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 7,781 tokens to every session, about $0.0389 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).