Borrowing it
Nothing to install: this file belongs to proofmath-owner/ai-filesystem-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/proofmath-owner/ai-filesystem-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/proofmath-owner/ai-filesystem-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/proofmath-owner/ai-filesystem-mcp/claude-md)<a href="https://agentmods.dev/instructions/proofmath-owner/ai-filesystem-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/proofmath-owner/ai-filesystem-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 5.1 | $0.00767 | $0.00767 |
| Opus 5 | $0.00383 | $0.00383 |
| Sonnet 5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
ai-filesystem-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 7d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code when working inside this repo.
What this repo is
A one-tool MCP server. The tool is transaction: apply N file operations as
one atomic batch with automatic rollback. That is the entire product surface.
It used to ship 39 commands (file I/O, search, git, code analysis, shell,
archives, …) and that overlap with your built-in tools is exactly why the
project was pared down. Everything but transaction was removed because you
already have it.
The contract
TransactionCommand (src/commands/implementations/batch/TransactionCommand.ts)
exposes an MCP tool with this shape — keep code, schema, and README aligned
on any change:
type |
Required | Behavior |
|---|---|---|
create |
path, content |
New file; mkdir -p parent. |
write |
path, content |
Overwrite existing file. |
update |
path, updates[] |
For each {oldText, newText} apply String.replace in order. |
move |
path, destination |
fs.rename. |
delete |
path |
unlink for files, rm -r for directories. |
rollbackOnError defaults to true. On failure, every operation that
already executed is reverted from a backup taken before the batch ran.
Architecture
src/index.ts MCP stdio server entry
└── core/ServiceContainer.ts Minimal DI, registers TransactionService
src/commands/registry/ BaseCommand / CommandRegistry / CommandLoader
src/commands/implementations/batch/TransactionCommand.ts
src/core/services/batch/TransactionService.ts on-disk backup + restore
~9 .ts files total. Keep it that way. No new tools without a very clear argument that the agent literally cannot do the thing on its own.
Conventions
- Every command extends
BaseCommand(src/commands/base/BaseCommand.ts): implementvalidateArgs()+executeCommand(), register inCommandLoader.loadCommands(). - Services come from the container:
context.container.getService<T>('transactionService'). - Errors: throw inside
executeCommand;BaseCommand.executeformats them. - Use
execFile(notexec) with array args anywhere shell is needed. - TS is strict-friendly.
npm run buildis plaintsc— do not reintroducetsc || true.
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.
- 7d ago First seen · 84 lines · 767 tokens per session scan A 75133a55d7b0
ai-filesystem-mcp CLAUDE.md is an instructions file published in the GitHub repository proofmath-owner/ai-filesystem-mcp (6 stars, last pushed 3mo ago), licensed MIT. It adds 767 tokens to every session, about $0.0038 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.
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.