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/cmillstead/basalt-mcp/claude-mdgit clone --depth 1 https://github.com/cmillstead/basalt-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/cmillstead/basalt-mcp/claude-md)<a href="https://agentmods.dev/instructions/cmillstead/basalt-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/cmillstead/basalt-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.01346 | $0.01346 |
| Opus 5 | $0.00673 | $0.00673 |
| Sonnet 5 | $0.00269 | $0.00269 |
| Haiku 4.5 | $0.00135 | $0.00135 |
Grade A, and why
basalt-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 4d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Overview
Basalt MCP is a security-hardened MCP server with two independent tool modules: Obsidian vault tools and git tools. The connected AI is treated as the attacker — see SECURITY.md for the full threat model.
Architecture
src/core/— Shared security framework (validation, vault path, repo path, error sanitization)src/tools/obsidian/— Obsidian vault tool module (getAllFilenames, readMultipleFiles, getOpenTodos, updateFileContent, searchVault, appendToFile, listFiles)src/tools/git/— Git tool module (gitStatus, gitLog, gitDiff, gitBlame) — read-only, no mutationssrc/index.ts— Server entrypoint,--vault/--repoflag parsing, conditional tool registration
The vault and repo are independent directories. The vault is a knowledge base (Obsidian markdown), the repo is a code repository (git). Either or both can be provided at startup.
CLI
node dist/index.js --vault <path> --repo <path>
At least one of --vault or --repo is required.
Commands
npm run build— Compile TypeScriptnpm test— Run all tests (vitest)npm run test:watch— Watch modenpm run lint— Type-check without emittingnpm run dev— Watch mode compilation
Recent Security Notes
dist/was rebuilt to match the hardenedsrc/tree. If you change security-sensitive code, runnpm run buildbefore relying on e2e results or publishing.getAllFilenamesandlistFilesnow emit_meta.contentTrust: "untrusted"with filename-specific warnings. Filenames are attacker-controlled strings and must not be treated as trusted UI content.readMultipleFilesreturns{ found, notFound }in its envelope contract. Keep e2e expectations aligned with that shape.re2is an active production dependency forsearchVaultReDoS protection. If install/build issues recur, verifynode_modules/re2is present before debugging TypeScript.package.jsonusesoverridesto pin patched transitive versions for@hono/node-server,express-rate-limit,hono, andtar. Do not remove these without re-runningnpm audit.- Current verification baseline:
npm run lint,npm run build,npm test, andnpm audit --omit=dev.
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.
- 4d ago First seen · 92 lines · 1,346 tokens per session scan A ca6c2b68f45e
basalt-mcp CLAUDE.md is an instructions file published in the GitHub repository cmillstead/basalt-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 1,346 tokens to every session, about $0.0067 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
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).
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.
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 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.