AgentToolDrop

33 of 48

CC Safety Net

Blocks destructive git and file commands and reads of secret files before a coding agent's tool call runs

  • score 35
  • 1.6k stars
  • 5.6 stars/day since creation
  • pushed
  • v2.6.12 on
  • MIT

Install into your coding CLIs with npx

npx -y cc-safety-net@latest install
npx -y cc-safety-net@latest doctor

Copied from the project's docs at github.com/kenryu42/cc-safety-net

Why you'd want it

CC Safety Net installs as a pre-execution hook in coding CLIs including Claude Code, Codex, Cursor, Gemini CLI, OpenCode and Copilot CLI, and parses what each command does, so wrapping it in bash -c or python -c or reordering flags does not hide it. It blocks commands such as git reset --hard, git push --force and rm -rf on dangerous targets, and access to SSH keys, .env files, ~/.aws and coding CLI credentials. Presets are tuned in a local GUI, official rulebooks add blocks for Terraform, AWS, gcloud and Azure, and committing .cc-safety-net/ shares the policy through git.

Best for

  • Stopping agent force pushes and hard resets
  • Keeping agents away from .env files and SSH keys
  • Teams running several coding CLIs

Use it when

You let a coding agent run shell commands and want a check that refuses destructive git and file operations before they execute.

Skip it if

You need containment: the README says it is not a sandbox and does not contain processes, set filesystem permissions or watch network egress. It is maintained mostly by one developer and needs Node.js 18 or higher.

Editor's note

The README says a broken config file never blocks anything, so a typo fails open rather than stopping the agent.

Related tools

Same category or shared tags.

  1. Spec Kit

    Devtool Standard

    Gives coding agents structured processes for spec-driven builds, bug fixes and idea assessment

    • 141k stars
    • 337 stars/day since creation
    • pushed
    • v1.2.0 on
    • MIT

    Install with uv and create a project

    uv tool install specify-cli
specify init my-project --integration copilot
    Use it when, skip it if, stats for Spec Kit

    Why you'd want it

    The specify CLI installs skills or command files for your coding agent, which you then run in chat: constitution once per project, then specify, plan, tasks, implement and converge for each feature. Optional extensions add a bug-fixing flow (assess, fix, test) and an idea assessment flow that ends in a go, clarify or stop decision, with reports saved as Markdown under .specify/. It has integrations for dozens of agents, including GitHub Copilot, Claude Code, Codex CLI, Cursor, Gemini CLI and Zed, and you can customize it with extensions, presets and workflows.

    Best for

    • Teams that want a spec before code
    • Keeping agent work reviewable step by step
    • Using one process across several coding agents

    Use it when

    You want a coding agent to work from a written specification, plan and task list rather than one prompt, with artifacts you review at each step.

    Skip it if

    Your changes are small enough that a single prompt does the job. The CLI needs Python 3.11+ and uv.

    Stats

    Stars per day, since repo creation
    337
    Release
    v1.2.0,
    License
    MIT
    Pricing
    Open source
    Works with
    Claude Code, Cursor, Codex, Gemini CLI, Zed, Linux, macOS, Windows
    Forks
    12,654
    Open issues
    171
    GitHub checked

    Full stat block for Spec Kit

  2. Rank 3

    ManimGX

    Devtool

    Renders Manim CE-style math and 3D animation videos from Python scenes your agent writes

    • score 72
    • 1.3k stars
    • 135 stars/day since creation
    • pushed
    • v0.1.1 on
    • MIT

    Install with pip

    pip install manimgx
    Use it when, skip it if, stats for ManimGX

    Why you'd want it

    ManimGX lets an agent write Python against Manim Community Edition's API while a Rust and wgpu engine renders the MP4. It handles 2D and 3D together, with LaTeX or Typst text and math that need no LaTeX installation. The manimgx inspect command gives the agent storyboards and 2D layout checks to review its own output. The README also lists speech synced to animations with self.say() and an npm package that runs scenes in the browser through Pyodide and WebGPU. The README reports a 90.6x speedup over ManimCE on its own five-scene benchmark on an Apple M4 Pro.

    Best for

    • Agent-made explainer videos
    • Math and 3D visualizations
    • Embedding animations in web pages

    Use it when

    You want an agent to turn a topic into a rendered math or 3D animation video, or you have Manim CE scenes you want to render faster.

    Skip it if

    You need a mature tool: the repo is days old, at v0.1.1, with two contributors. It needs Python 3.13+, and the README says native wheels include x264 and are GPL-3.0-or-later as a whole, so check that before redistributing. The prompt install has your agent follow a remote llms.txt and run setup commands, so read it first. The benchmark numbers are the README's own claims.

    Stats

    New and rising score
    72 of 100
    Stars per day, since repo creation
    135
    Release
    v0.1.1,
    License
    MIT
    Pricing
    Open source
    Works with
    Claude Code, Cursor, Codex, macOS, Linux, Windows, Web
    Forks
    90
    Open issues
    9
    GitHub checked

    Full stat block for ManimGX

  3. Rank 7

    Open Code Review

    Devtool

    Reviews Git diffs with a deterministic rule layer plus an LLM agent and writes line-level review comments

    • score 61
    • 47.3k stars
    • 314 stars/day since creation
    • pushed
    • v1.13.0 on
    • Apache-2.0

    Install with npm

    npm install -g @alibaba-group/open-code-review
    Use it when, skip it if, stats for Open Code Review

    Why you'd want it

    Open Code Review is a CLI that reads Git diffs and sends changed files to a configurable LLM through an agent that can read full files and search the codebase. Deterministic code, not the model, handles file selection, bundling of related files into sub-agent review units, and matching review rules to each file. Besides diff review, ocr scan reviews whole files, and delegation mode lets your own coding agent do the review so no OCR API key is needed. The docs list CI integrations for GitHub Actions, GitLab CI, GitFlic CI and Gerrit, and plugins for Claude Code, Codex, Cursor, Kimi Code and OpenCode.

    Best for

    • Reviewing pull requests in CI
    • Rule-driven review of large changesets
    • Giving a coding agent a review command

    Use it when

    You want a code review step that runs from the command line or CI and keeps file selection and rule matching in fixed code instead of in a prompt.

    Skip it if

    You need high recall; the README says its recall is lower than general-purpose agents, a deliberate trade-off for precision. It needs Git 2.41 or newer and, outside delegation mode, an LLM provider with an API key you enter, and it sends changed files to that endpoint. The README links an OpenTelemetry telemetry page, so read it before using the tool on private code. The repo is about five months old and ships releases every few days.

    Stats

    New and rising score
    61 of 100
    Stars per day, since repo creation
    314
    Release
    v1.13.0,
    License
    Apache-2.0
    Pricing
    Open source
    Works with
    Claude Code, Codex, Cursor, macOS, Linux, Windows
    Forks
    3,444
    Open issues
    311
    GitHub checked

    Full stat block for Open Code Review

For agents

The same entry, as files an agent can read without scraping this page. 

# read one entry
curl -s https://agenttooldrop.com/tools/cc-safety-net.md

# list the MCP servers in the catalog
curl -s https://agenttooldrop.com/tools.json \
  | jq -r '.tools[] | select(.category=="mcp-server") | .slug'