What is fuse CLAUDE.md?

Project instructions for Fuse, a local firewall that checks shell commands and MCP tool calls before they run. It assigns each command a risk level, from safe to blocked.

It is for understanding Fuse's Go project structure, supported platforms, command-classification rules, and development workflow.

It helps prevent an AI agent from running risky commands without the right level of review or approval.

How php-workx/fuse configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to php-workx/fuse. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/php-workx/fuse/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/php-workx/fuse

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/php-workx/fuse/claude-md/github.svg)](https://agentmods.dev/instructions/php-workx/fuse/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/php-workx/fuse/claude-md"><img src="https://agentmods.dev/badge/instructions/php-workx/fuse/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/php-workx/fuse/claude-md"><img src="https://agentmods.dev/badge/instructions/php-workx/fuse/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,647 This file is loaded in full into every session.

When invoked 1,647 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01647	$0.01647
Opus 5.5	$0.00659	$0.00659
Sonnet 5.5	$0.00329	$0.00329
Haiku 4.5	$0.00165	$0.00165

Measured 1mo ago against content hash bf824e3f3619, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fuse 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 1mo 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.

CLAUDE.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Fuse

What is Fuse?

Fuse is a local firewall for AI agent commands. It classifies shell commands and MCP tool calls into four decision levels — SAFE, CAUTION, APPROVAL, BLOCKED — and gates execution accordingly. In proxy and run modes, fuse controls execution directly. In hook mode, fuse advises the agent. Everything runs locally with no cloud dependencies.

Tech Stack

Language: Go 1.25
Build: just (not Make) — see justfile for all targets
Platforms: macOS (darwin/arm64, amd64), Linux (linux/amd64, arm64), Windows (windows/amd64, arm64). Windows is fully supported: PowerShell and CMD shell strategy, Console API approval prompts (CONIN$/CONOUT$), Job Object process management, and Windows-native security rules (PowerShell/CMD attack patterns, LOLBins, registry, persistence) are all merged. PowerShell/Batch script inspection is line-oriented (here-strings, splatting, ^ line-continuations are not reconstructed before matching). See specs/done/windows-support-plan.md.
Dependencies: Minimal. Pure-Go SQLite (modernc.org/sqlite), shell parser (mvdan.cc/sh), Cobra CLI, YAML. No RPC/cloud SDKs.

Project Layout

cmd/fuse/              Entry point (thin main.go)
internal/
  cli/                 Cobra commands: install, doctor, run, proxy, hook, events, dryrun, enable/disable
  core/                Classification pipeline, normalization, safe-command detection, sanitization
  policy/              Built-in preset rules (git, aws, gcp, k8s, security) + user YAML policy evaluation
  adapters/            Runtime adapters:
    hook.go              Claude Code PreToolUse hook (classify-only)
    native_file_policy.go  Claude native file tool (Read/Write/Edit/MultiEdit) path protection
    codexshell.go        Codex shell MCP server (concurrent JSON-RPC)
    mcpproxy.go          Generic MCP proxy with tool interception
    runner.go            Shell execution wrapper (run mode)
  approve/             Approval lifecycle: HMAC-signed records, TUI prompt via /dev/tty
  config/              YAML config loading, XDG paths
  db/                  SQLite state storage (WAL mode, schema migrations v1-v4, event log)
  inspect/             File inspection for scripts (shell, python, javascript)
  events/              Event types and formatting
  releasecheck/        Shell compatibility release checks (bash/zsh/fish)
testdata/fixtures/     Test fixtures including commands.yaml
specs/                 Technical and functional specifications

Read the full file on GitHub · 136 lines

Changes

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.

1mo ago First seen · 136 lines · 1,647 tokens per session scan A bf824e3f3619

Subscribe to this mod's changes

fuse CLAUDE.md is an instructions file published in the GitHub repository php-workx/fuse (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,647 tokens to every session, about $0.0066 per session on Opus 5.5. 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.

AI Safety Claude Code Go Security cli codex developer-tools

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).

microsoft/vscode · 9,715 tokens

fuse: Instructions file for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md — Fuse

What is Fuse?

Tech Stack

Project Layout

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

vscode oss-third-party-notices.instructions.md

langchain AGENTS.md

vscode copilot-instructions.md

vscode model-prompts.instructions.md