Skip to content
Back to search

vet

Find issues worth your attention.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/imbue-ai-vet/badge.svg)](/listings/imbue-ai-vet)

HTML

<a href="/listings/imbue-ai-vet"><img src="/api/listings/imbue-ai-vet/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These steps run a script from the network that findsafeskills does not scan.

curl -fsSL https://raw.githubusercontent.com/imbue-ai/vet/main/install-skill.sh | bash

You will be prompted to choose between:

- **Project level**: installs into `.agents/skills/vet/`, `.opencode/skills/vet/`, `.claude/skills/vet/`, and `.codex/skills/vet/` at the repo root (run from your repo directory) - **User level**: installs into `~/.agents/`, `~/.opencode/`, `~/.claude/`, and `~/.codex/` skill directories, discovered globally by all agents

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 279 lines · 1 finding marked

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <p align="center">
  2. <a href="https://github.com/imbue-ai/vet">
  3. <img alt="Vet: Verify Everything" src="https://raw.githubusercontent.com/imbue-ai/vet/main/images/Vet.svg" width="21%">
  4. </a>
  5. </p>
  6. <p align="center">
  7. <a href="https://pypi.python.org/pypi/verify-everything/"><img src="https://img.shields.io/pypi/v/verify-everything.svg" alt="PyPi"></a>
  8. <a href="https://www.gnu.org/licenses/agpl-3.0"><img src="https://img.shields.io/badge/License-AGPL_v3-blue.svg" alt="License: AGPL v3"></a>
  9. <img src="https://github.com/imbue-ai/vet/actions/workflows/test-unit.yml/badge.svg" alt="Build Status">
  10. <a href="https://discord.gg/sBAVvHPUTE"><img src="https://img.shields.io/badge/Discord-Join%20us-5865F2?logo=discord&logoColor=white" alt="Discord"></a>
  11. </p>
  12. <p align="center">Vet is a standalone verification tool for <b>code changes</b> and <b>coding agent behavior</b>.</p>
  13. ## Why Vet
  14. - **Reviews intent and code**: checks agent conversations for goal adherence and code changes for correctness.
  15. - **Runs anywhere**: from the terminal, as an agent skill, or in CI.
  16. - **Bring-your-own-model**: works with any provider using your own API keys.
  17. - **Works with existing subscriptions**: supports Anthropic and OpenAI subscriptions using [`--agentic`](#usage).
  18. - **Free and open source**: no account, fees, or data collection. Requests go directly to your inference provider. Licensed under the AGPL-3.0.
  19. <p align="center">
  20. <a href="https://github.com/imbue-ai/vet">
  21. <img alt="Vet: Verify Everything" src="https://raw.githubusercontent.com/imbue-ai/vet/main/images/vet_example.png" width="100%">
  22. </a>
  23. </p>
  24. ## Using Vet with Coding Agents
  25. Vet includes an agent skill. When installed, agents will proactively run vet after code changes to find issues with the new code and mismatches between the user's request and the agent's actions.
  26. ### Install the skill
  27. ```bash
  28. curl -fsSL https://raw.githubusercontent.com/imbue-ai/vet/main/install-skill.sh | bash
    • Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
    • Line 37 on GitHub
  29. ```
  30. You will be prompted to choose between:
  31. - **Project level**: installs into `.agents/skills/vet/`, `.opencode/skills/vet/`, `.claude/skills/vet/`, and `.codex/skills/vet/` at the repo root (run from your repo directory)
  32. - **User level**: installs into `~/.agents/`, `~/.opencode/`, `~/.claude/`, and `~/.codex/` skill directories, discovered globally by all agents
  33. ### Demo
  34. ![demo](https://raw.githubusercontent.com/imbue-ai/vet/main/images/demo.gif)
  35. <details>
  36. <summary>Manual installation</summary>
  37. #### Project Level
  38. From the root of your git repo:
  39. ```bash
  40. for dir in .agents .opencode .claude .codex; do
  41. mkdir -p "$dir/skills/vet/scripts"
  42. for file in SKILL.md scripts/export_opencode_session.py scripts/export_codex_session.py scripts/export_claude_code_session.py; do
  43. curl -fsSL "https://raw.githubusercontent.com/imbue-ai/vet/main/skills/vet/$file" \
  44. -o "$dir/skills/vet/$file"
  45. done
  46. done
  47. ```
  48. #### User Level
  49. ```bash
  50. for dir in ~/.agents ~/.opencode ~/.claude ~/.codex; do
  51. mkdir -p "$dir/skills/vet/scripts"
  52. for file in SKILL.md scripts/export_opencode_session.py scripts/export_codex_session.py scripts/export_claude_code_session.py; do
  53. curl -fsSL "https://raw.githubusercontent.com/imbue-ai/vet/main/skills/vet/$file" \
  54. -o "$dir/skills/vet/$file"
  55. done
  56. done
  57. ```
  58. </details>
  59. ### Security note
  60. The `--history-loader` option executes the specified shell command as the current user to load the conversation history. It is important to review history loader commands and shared config presets before use.
  61. ## Install the CLI
  62. ```bash
  63. pip install verify-everything
  64. ```
  65. Or with [pipx](https://pipx.pypa.io/):
  66. ```bash
  67. pipx install verify-everything
  68. ```
  69. Or with [uv](https://docs.astral.sh/uv/):
  70. ```bash
  71. uv tool install verify-everything
  72. ```
  73. ### Usage
  74. Run Vet in the current repo:
  75. ```bash
  76. vet "Implement X without breaking Y"
  77. ```
  78. Compare against a base ref/commit:
  79. ```bash
  80. vet "Refactor storage layer" --base-commit main
  81. ```
  82. Use Claude Code, Codex, or OpenCode instead of LLM APIs (`--agent-harness`: `claude`, `codex`, `opencode`):
  83. ```bash
  84. vet "Implement X without breaking Y" --agentic --agent-harness claude
  85. ```
  86. ## GitHub PRs (Actions)
  87. Vet reviews pull requests using a reusable GitHub Action.
  88. Create `.github/workflows/vet.yml`:
  89. ```yaml
  90. name: Vet
  91. permissions:
  92. contents: read
  93. pull-requests: write
  94. on:
  95. pull_request:
  96. types: [opened, edited, synchronize, reopened]
  97. jobs:
  98. vet:
  99. if: github.event.pull_request.draft == false
  100. runs-on: ubuntu-latest
  101. env:
  102. ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
  103. steps:
  104. - uses: actions/checkout@v4
  105. with:
  106. ref: ${{ github.event.pull_request.head.sha }}
  107. fetch-depth: 0
  108. - uses: imbue-ai/vet@main
  109. with:
  110. agentic: false
  111. ```
  112. The action handles Python setup, vet installation, merge base computation, and posting the review to the PR. `ANTHROPIC_API_KEY` must be set as a repository secret when using Anthropic models (the default). See [`action.yml`](https://github.com/imbue-ai/vet/blob/main/action.yml) for all available inputs.
  113. ## How it works
  114. Vet snapshots the repo and diff, optionally adds a goal and agent conversation, runs LLM checks, then filters/deduplicates findings into a final list of issues.
  115. ![architecture](https://raw.githubusercontent.com/imbue-ai/vet/main/images/architecture.svg)
  116. ## Output & exit codes
  117. - Exit code `0`: no issues found
  118. - Exit code `1`: unexpected runtime error
  119. - Exit code `2`: invalid usage/configuration error
  120. - Exit code `10`: issues found
  121. Output formats:
  122. - `text`
  123. - `json`
  124. - `github`
  125. ## Configuration
  126. ### Model configuration
  127. Vet supports custom model definitions using OpenAI-compatible endpoints via JSON config files searched in:
  128. - `$XDG_CONFIG_HOME/vet/models.json` (or `~/.config/vet/models.json`)
  129. - `.vet/models.json` at your repo root
  130. #### Example `models.json`
  131. ```json
  132. {
  133. "providers": {
  134. "openrouter": {
  135. "name": "OpenRouter",
  136. "api_type": "openai_compatible",
  137. "base_url": "https://openrouter.ai/api/v1",
  138. "api_key_env": "OPENROUTER_API_KEY",
  139. "models": {
  140. "gpt-5.2": {
  141. "model_id": "openai/gpt-5.2",
  142. "context_window": 400000,
  143. "max_output_tokens": 128000,
  144. "supports_temperature": true
  145. },
  146. "kimi-k2": {
  147. "model_id": "moonshotai/kimi-k2",
  148. "context_window": 131072,
  149. "max_output_tokens": 32768,
  150. "supports_temperature": true
  151. }
  152. }
  153. }
  154. }
  155. }
  156. ```
  157. Then:
  158. ```bash
  159. vet "Harden error handling" --model gpt-5.2
  160. ```
  161. ### Model registry
  162. Vet maintains a remote model registry with community-contributed model definitions. To fetch the latest definitions without upgrading vet:
  163. ```bash
  164. vet --update-models
  165. ```
  166. This downloads model definitions from the [registry](https://github.com/imbue-ai/vet/blob/main/registry/models.json) and caches them locally at `~/.cache/vet/remote_models.json`. Once cached, registry models appear in `vet --list-models` and can be used with `--model` like any other model.
  167. Model resolution priority (highest to lowest):
  168. 1. User config (`.vet/models.json` or `~/.config/vet/models.json`)
  169. 2. Builtin models (Anthropic, OpenAI, Gemini)
  170. 3. Registry models (cached via `--update-models`)
  171. See [`registry/CONTRIBUTING.md`](https://github.com/imbue-ai/vet/blob/main/registry/CONTRIBUTING.md) for information about contributing model definitions to the registry.
  172. ### Configuration profiles (TOML)
  173. Vet supports named profiles so teams can standardize CI usage without long CLI invocations.
  174. Profiles set defaults like model choice, enabled issue codes, output format, and thresholds.
  175. See [the example](https://github.com/imbue-ai/vet/blob/main/.vet/configs.toml) in this project.
  176. ### Custom issue guides
  177. You can customize the guide text for the issue codes via `guides.toml`. Guide files are loaded from:
  178. - `$XDG_CONFIG_HOME/vet/guides.toml` (or `~/.config/vet/guides.toml`)
  179. - `.vet/guides.toml` at your repo root
  180. #### Example `guides.toml`
  181. ```toml
  182. [logic_error]
  183. suffix = """
  184. - Check for integer overflow in arithmetic operations
  185. """
  186. [insecure_code]
  187. replace = """
  188. - Check for SQL injection: flag any string concatenation or f-string formatting used to build SQL queries rather than parameterized queries
  189. - Check for XSS: flag user-supplied data rendered into HTML templates without proper escaping or sanitization
  190. - Check for path traversal: flag file operations where user input flows into file paths without validation against directory traversal (e.g. ../)
  191. - Check for insecure cryptography: flag use of deprecated or weak algorithms (e.g. MD5, SHA1 for security purposes, DES, RC4)
  192. - Check for hardcoded credentials: flag passwords, API keys, or tokens embedded directly in source code
  193. """
  194. ```
  195. Section keys must be valid issue codes (`vet --list-issue-codes`). Each section supports three optional fields: `prefix` (prepends to built-in guide), `suffix` (appends to built-in guide), and `replace` (fully replaces the built-in guide). `prefix` and `suffix` can be used together, but `replace` is mutually exclusive with the other two. Guide text should be formatted as a list.
  196. ## Community
  197. New to Vet? [Read the launch post](https://imbue.com/product/vet/) for an intro and 2-minute demo.
  198. Join the [Imbue Discord](https://discord.gg/sBAVvHPUTE) for discussion, questions, and support. For bug reports and feature requests, please use [GitHub Issues](https://github.com/imbue-ai/vet/issues).
  199. ## License
  200. This project is licensed under the [GNU Affero General Public License v3.0 (AGPL-3.0-only)](https://github.com/imbue-ai/vet/blob/main/LICENSE).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.