Borrowing it
Nothing to install: this file belongs to Gallucky/jarvis-mcp-server. 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/Gallucky/jarvis-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/Gallucky/jarvis-mcp-serverWrote 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/gallucky/jarvis-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/gallucky/jarvis-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/gallucky/jarvis-mcp-server/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/gallucky/jarvis-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/gallucky/jarvis-mcp-server/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 | $0.01629 | $0.01629 |
| Opus 5 | $0.00814 | $0.00814 |
| Sonnet 5 | $0.00326 | $0.00326 |
| Haiku 4.5 | $0.00163 | $0.00163 |
Grade A, and why
jarvis-mcp-server 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 8d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
jarvis-mcp-server
Personal MCP server running on a home mini PC, exposed via Tailscale. Built with TypeScript + Express + better-sqlite3.
Stack
src/index.ts— Express server, OAuth 2.1, MCP transportsrc/tools/— one file per domain:vault.ts,sqlite.ts,filesystem.ts,jarvis.ts,study/psychometric.tssrc/services/db.ts— single better-sqlite3 connection todata/jarvis.dbsrc/services/obsidianClient.ts— wraps Obsidian Local REST APIsrc/routes/dashboard.ts—/dashboard(home hub HTML shell),/dashboard/study(study HTML shell) +/api/stats(JSON)src/dashboard/— React UI source:home/(OS hub),study/(study tracker),shared/(RingChart, shared.css) — two esbuild entry points bundled intopublic/home.{js,css}andpublic/study.{js,css}src/scripts/syncCheckboxes.ts— parses vault homework markdown → SQLitesrc/scripts/migrate.ts— applies SQL files frommigrations/migrations/— numbered.sqlfiles (currently:001_exercise_completions.sql)
Key conventions
- New tool domain → new file in
src/tools/, matching schema insrc/schemas/, register inbuildServer()inindex.ts - New DB table → new file in
migrations/, runnpm run migrate - Path safety: all
fs_*tools run throughsrc/utils/pathSafety.ts(allowlist insrc/constants.ts) - Dashboard is two real React apps under
src/dashboard/{home,study}/, sharingsrc/dashboard/shared/(RingChart component, shared.css with fonts/reset/card/ring rules via@import). Bundled locally with esbuild (two named entry points,home=...andstudy=...) — no CDN dependency, works with no outbound internet access.src/routes/dashboard.tsonly serves HTML shells + JSON API;src/dashboard/is excluded from the maintscbuild (tsconfig.jsonexcludes it; that folder has its owntsconfig.jsonfor editor JSX/DOM support) /dashboardis the OS-level hub: a grid of blocks (home/components/HomeBlock.tsx). Each block is either a live link (hrefset, e.g. the study tracker with its progress ring) or an unlinked "בקרוב" (coming soon) placeholder for future tools (home/components/Home.tsx'sIDEA_BLOCKSarray) — turning a placeholder into a real feature is just addinghref/pctto its entry- Dashboard font is self-hosted Rubik (
public/fonts/Rubik-{hebrew,latin}.woff2, committed to the repo — not a build artifact; onlyhome.{js,css}/study.{js,css}are gitignored).shared.cssholds the@font-facerules; esbuild's--external:/fonts/*keeps thoseurl()paths root-relative instead of trying to resolve them on disk - The study page's "לפי שיעור" lesson tiles link to
obsidian://open?vault=...&file=...using the hardcodedVAULT_NAMEinstudy/components/Study.tsx— update it if the vault is ever renamed
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.
- 8d ago First seen · 96 lines · 1,629 tokens per session scan A 669aa958e741
jarvis-mcp-server CLAUDE.md is an instructions file published in the GitHub repository Gallucky/jarvis-mcp-server (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,629 tokens to every session, about $0.0081 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
plan-forge caching.instructions.md
Caching patterns for .NET — IDistributedCache, Redis, in-memory, cache-aside, TTL strategies.
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.