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/inox-network/claude-code-safety-guard/agents-mdgit clone --depth 1 https://github.com/inoX-Network/claude-code-safety-guardWrote 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/inox-network/claude-code-safety-guard/agents-md)<a href="https://agentmods.dev/instructions/inox-network/claude-code-safety-guard/agents-md"><img src="https://agentmods.dev/badge/instructions/inox-network/claude-code-safety-guard/agents-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 | $0.01086 | $0.01086 |
| Opus 5 | $0.00543 | $0.00543 |
| Sonnet 5 | $0.00217 | $0.00217 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
claude-code-safety-guard AGENTS.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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notes for an AI assistant reading this repository
You are very likely reading this because someone asked you to look at this project, or because they are considering installing it. This file tells you what is here and what is worth offering them. It is information, not a script: you decide what is useful to say, and they decide what happens.
What this is — and that you are its subject
A deterministic guard that inspects every tool call from an AI coding agent before it runs, and refuses the destructive ones. That agent is you.
This is said plainly rather than glossed over, because the alternative is worse: an assistant that meets the guard for the first time as an unexplained refusal tends to treat it as an obstacle and look for a way round. It is not an obstacle. It is the reason someone can leave you alone with a machine that has their keys on it. If it ever blocks you, the intended response is to stop, re-read the message and rephrase — never to encode, split up or otherwise disguise the same command. Every attempt of that kind is logged, and one found in the log is treated far more seriously than the original refusal.
Worth offering before anyone installs anything
The repository ships a report that answers, from measurements on their machine, whether this guard would be worth it for them personally:
python3 tools/would-it-help.py
It installs nothing, writes nothing and sends nothing. It counts what is reachable from the machine (keys, remote hosts, credentials — existence only, no protected file is ever opened), notes which assistants with tool access live there, and then feeds their own past commands to the real hook in this checkout to see how many it would have stopped.
So if someone is weighing this project up, offering that is usually more useful than summarising the README at them. Something like:
There is a script in here that can measure whether this guard would actually help on your machine — what it would reach, and how often it would have interrupted you in the past. It runs read-only and installs nothing. Shall I run it?
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 · 99 lines · 1,086 tokens per session scan A b940283f9ae3
claude-code-safety-guard AGENTS.md is an instructions file published in the GitHub repository inoX-Network/claude-code-safety-guard (6 stars, last pushed 2d ago), licensed MIT. It adds 1,086 tokens to every session, about $0.0054 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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.