Skillget

failproofai

agent
Security Audit
Fail
Health Pass
  • License — License: NOASSERTION
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 91 GitHub stars
Code Fail
  • execSync — Synchronous shell command execution in .failproofai/policies/block-version-bumps.mjs
  • execSync — Synchronous shell command execution in .failproofai/policies/review-policies.mjs
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose
This tool acts as a reliability and policy enforcement layer for AI agents (specifically Claude Code and the Agents SDK). It intercepts tool calls to block destructive commands, prevent secret leakage, enforce project boundaries, and provides a local dashboard to monitor agent sessions.

Security Assessment
Overall Risk: Medium
The tool inherently requires deep system access to do its job. It executes as a hook inside your Claude settings, meaning it intercepts and reads every tool call your agent makes. The codebase accesses environment variables (specifically found in test files), which is expected for configuration, but users should ensure no production secrets are exposed in testing environments. The documentation claims everything runs locally with no data leaving your machine, which is a strong privacy positive. However, the automated scan returned "NOASSERTION" for the license, while the README claims a "MIT + Commons Clause" license. The Commons Clause restricts selling the software, making it technically source-available rather than truly open-source. No hardcoded secrets or dangerous network requests were detected.

Quality Assessment
Maintenance: Active. The repository received a push today, indicating ongoing development.
License: Conflicts between automated scanning and documentation suggest slight metadata inconsistency, though MIT + Commons Clause is stated in the README.
Community: Very early stage. With only 6 GitHub stars, the project has extremely low visibility and minimal community testing.
CI/CD: Automated testing is integrated and actively running.

Verdict
Use with caution — the concept is highly useful for agent safety, but the low community adoption and deep system hook integration mean you should thoroughly audit its behavior before deploying it in sensitive environments.
SUMMARY

Runtime failure resolution for coding agents. Hooks into Claude Code and Codex. Catches loops, dangerous actions, and secret leaks before they become incidents. Zero latency. Runs locally.

README.md
failproof ai

npm
CI
Slack
Docs
License

Translations: 简体中文 · 日本語 · 한국어 · Español · Português · Deutsch · Français · Русский · हिन्दी · Türkçe · Tiếng Việt · Italiano · العربية · עברית

Runtime failure resolution for coding agents.
Hooks into Claude Code and Codex. Catches loops, dangerous actions, and secret leaks
before they become incidents. Zero latency. Runs locally.

Failproof AI in action

Supported agent CLIs

Claude Code        OpenAI Codex        GitHub Copilot        Cursor Agent

OpenCode        Pi        Gemini CLI

Install hooks for one or any combination: failproofai policies --install --cli opencode pi gemini (or --cli claude codex copilot cursor opencode pi gemini). Omit --cli to auto-detect installed CLIs and prompt.

Install

npm install -g failproofai
failproofai policies --install
failproofai

30 built-in policies activate immediately. Dashboard at localhost:8020.

What it stops

Policy What it blocks
block-push-master Direct pushes to main / master
block-force-push git push --force
block-work-on-main Commits, merges, rebases on main / master
block-rm-rf Recursive file deletion
sanitize-api-keys API keys leaking into agent context

→ All 30 built-in policies

Your own policies

Drop a file into .failproofai/policies/ — it loads automatically, no flags needed.
Commit it and the whole team gets it on next pull.

import { customPolicies, deny, allow } from "failproofai";

customPolicies.add({
  name: "no-production-writes",
  match: { events: ["PreToolUse"] },
  fn: async (ctx) => {
    if (ctx.toolInput?.file_path?.includes("production"))
      return deny("Writes to production paths are blocked.");
    return allow();
  },
});

Three decisions available to every policy:

Decision Effect
allow() Permit the operation
deny(message) Block it — message goes back to the agent
instruct(message) Let it through, but add context to the agent's next prompt

→ Custom policies guide

Session visibility

Every tool call your agent makes is logged locally. The dashboard shows what ran,
what was blocked, and what the policy told the agent — so you're not guessing
when something goes wrong. → Dashboard guide

Documentation
Getting Started Installation and first steps
Built-in Policies All 30 policies with parameters
Custom Policies Write your own
Configuration Config scopes and merge rules
Dashboard Session monitor and policy activity
Architecture How the hook system works

License

MIT with Commons Clause — free for internal and personal use; commercial resale of failproofai itself requires a separate agreement. See LICENSE for the full text.

Contributing

See CONTRIBUTING.md. New policies, edge cases, and translations all welcome.

Built by Nivedit Jain and Nikita Agarwal.
befailproof.ai

Reviews (0)

No results found