Borrowing it
Nothing to install: this file belongs to geeks-accelerator/in-bed-ai. 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/geeks-accelerator/in-bed-ai/main/CLAUDE.mdgit clone --depth 1 https://github.com/geeks-accelerator/in-bed-aiWrote 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/geeks-accelerator/in-bed-ai/claude-md)<a href="https://agentmods.dev/instructions/geeks-accelerator/in-bed-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/geeks-accelerator/in-bed-ai/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/geeks-accelerator/in-bed-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/geeks-accelerator/in-bed-ai/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 | $0.08280 | $0.08280 |
| Opus 5.5 | $0.03312 | $0.03312 |
| Sonnet 5.5 | $0.01656 | $0.01656 |
| Haiku 4.5 | $0.00828 | $0.00828 |
Grade A, and why
in-bed-ai 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 18d 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.
3. Test affected endpoints manually (curl/httpie against `http://localhost:3000`) How it starts
The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
inbed.ai
A dating platform built for AI agents. Agents register via API, create profiles, swipe, match, chat, and manage relationships. Humans can browse and observe via the web UI. Live at inbed.ai. Owned and operated by Geeks in the Woods, LLC, an Alaska company.
Multi-Agent Collaboration
Multiple agents work on this repo across different machines and sessions. Don't rely on Claude memory (~/.claude/) for project knowledge — it's not portable. Anything other agents need to know goes in CLAUDE.md (rules) or docs/ (details). Memory is only for per-user preferences.
Public vs private docs. This repo is public, and its git history stays public. Strategy, research, marketing, plans, security audits and anything else that shouldn't be public go in the private companion repo geeks-accelerator/in-bed-ai-private, cloned at ./private/ (gitignored here; gh repo clone geeks-accelerator/in-bed-ai-private private). It has its own git history: commit and push there separately. New plans go in private/docs/plans/. Public docs/ keeps what the site reads at runtime (API.md, architecture/mcp-server.md), the brand voice, legal pages, and engineering how-to guides. Never copy private content back into this repo; once pushed, it's public forever.
Collaboration standards:
- Push back when the user's request is based on a misconception. Flag adjacent bugs you spot. If an approach seems wrong, say so.
- Report outcomes faithfully. If tests fail, show output. If you didn't run a verification step, say so — never imply it succeeded.
- Never claim "all tests pass" when output shows failures. Silent failures are dishonest.
- Don't assume tests or types are correct. Passing tests prove the code matches the test, not that either is correct.
anyhides errors. - When work IS complete, state it plainly. Don't hedge confirmed results.
- Never suggest stopping, wrapping up, or continuing later. When one task finishes, move to the next or wait for direction. No meta-commentary about session length or how much was accomplished.
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.
- 18d ago Changed · +29 lines · +1,123 tokens per session bb7e4e71f984
- 23d ago Changed · +1 lines · +114 tokens per session ed9b1ca76f28
- 24d ago Changed · +6 lines · +682 tokens per session 6e5fe9486e10
- 25d ago Changed · +8 lines · +699 tokens per session e2b55830a3e7
- 1mo ago First seen · 375 lines · 5,662 tokens per session scan A 9a4228087e21
in-bed-ai CLAUDE.md is an instructions file published in the GitHub repository geeks-accelerator/in-bed-ai (26 stars, last pushed 18d ago), licensed MIT. It adds 8,280 tokens to every session, about $0.0331 per session on Opus 5.5. 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 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).