Borrowing it
Nothing to install: this file belongs to ravenintheforrest/aiden-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/ravenintheforrest/aiden-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/ravenintheforrest/aiden-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/ravenintheforrest/aiden-mcp/claude-md)<a href="https://agentmods.dev/instructions/ravenintheforrest/aiden-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ravenintheforrest/aiden-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/ravenintheforrest/aiden-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ravenintheforrest/aiden-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 | $0.01281 | $0.01281 |
| Opus 5 | $0.00641 | $0.00641 |
| Sonnet 5 | $0.00256 | $0.00256 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
aiden-mcp 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 9d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aiden-mcp — project map
Unofficial MCP server for the Fellow Aiden coffee brewer. Lets Claude push/list/delete/share brew profiles on the Aiden over Fellow's private API, scrape coffee details from roaster product pages, and apply Aiden-specific brewing heuristics to design a recipe. TypeScript, runs as a Cloudflare Worker (Streamable-HTTP MCP transport + OAuth 2.0). Pairs with the Fellow_Aiden MCP connector; vault notes live at 05) maker/aiden-mcp.
Auto-loads when Claude opens
~/dev/aiden-mcp. Read this first, then use the routing table. This repo has a GitHub remote (ravenintheforrest/aiden-mcp) — commitTASKS.md/SESSIONS.mdso resume travels.
Where things live
- Machine: 🐧 dev/build on ravelab. Deploys to Cloudflare Workers (
npx wrangler deploy) — live athttps://aidenmcp.ravenhoward.org/mcp. There is no long-running local server; the Worker is the runtime. - State: none persistent. Cloudflare KV (
AIDEN_OAUTH) holds only short-lived records — auth codes ≤10min, access tokens ≤1hr, client regs ≤90d. Only Fellow-issued JWTs are stored, never the Fellow password. - Secrets: Cloudflare Worker secrets (
npx wrangler secret put …) — canary account creds + webhook. Local dev vars in.dev.vars(untracked). Never in-repo. - Auth model: OAuth 2.0 auth-code + PKCE, or
X-Fellow-Email/X-Fellow-Passwordheaders. Password reaches server once at/oauth/authorize, exchanged for a Fellow JWT, then discarded. - Profile data (temperature/ratio priors) is harvested, not folk wisdom — see
data/.
Folder map
src/index.ts— Worker entry: HTTP routing, MCP server, tool registration, header auth.src/fellow-api.ts— calls to Fellow's private API (list/create/update/delete/share, device info).src/auth.ts— Fellow/auth/login→ JWT.src/fellow-schemas.ts— zod contracts for Fellow API responses (drift detection).src/validation.ts— client-side profile validation before write (clear errors, not 400s).src/coffee-fetcher.ts—fetch_coffee_details: scrape Shopify roaster pages → structured coffee data.src/brewing-guidelines.ts—brewing_guidelines: Aiden brewing heuristics + starting recipe.src/grinders.ts— grind-setting conversions across grinder models.src/flash-brew.ts—flash_brew: Japanese iced coffee plan + dose workaround.src/canary.ts— hourly cron probe of Fellow API for drift; fingerprinted alerts to webhook.src/oauth/— OAuth flow:authorize.ts,token.ts,register.ts(dynamic client reg),discovery.ts(well-known metadata),kv.ts(KV helpers).data/— profile datasets (brew-talks-profiles.csv= primary 145,fellow-drops-profiles.csv) +README.md.scripts/—fetch-brew-talks.py,drops-stats.py— regenerate/analyze the datasets.wrangler.toml— Worker config: KV binding, hourly cron trigger, custom domain notes.
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.
- 9d ago First seen · 53 lines · 1,281 tokens per session scan A 03a3ce8bf763
aiden-mcp CLAUDE.md is an instructions file published in the GitHub repository ravenintheforrest/aiden-mcp (8 stars, last pushed 15d ago), licensed MIT. It adds 1,281 tokens to every session, about $0.0064 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
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).
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).
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.