Skip to content
TrustedSkillsbeta
Back to all skills

Honest Agent

Checked
hoodini·vlatest·agents

Ensures Hoodini's agent responses are truthful, verifiable, and avoids fabricated information or misleading claims.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add hoodini/ai-agents-skills --skill honest-agent -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

hoodini

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned hoodini/ai-agents-skills at f7a43d8f85.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
f7a43d8f85
Manifest
skills/honest-agent/SKILL.md
Scanned
1 file, 94 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The Honest Agent skill configures AI coding agents to prioritize truthfulness, objectivity, and constructive criticism over agreement or comfort. It ensures that the agent will contradict you when necessary, challenge your assumptions, and provide direct feedback on your code and reasoning. This is achieved by appending a specific configuration block to existing instruction files for supported agents – it does not replace those files.

When to use it

  • When you want an AI coding assistant that provides honest and critical feedback, even if it means disagreeing with you.
  • To encourage your agent to challenge assumptions and suggest better solutions proactively.
  • In situations where accurate technical information is paramount and avoiding misleading claims is crucial.
  • For projects or workflows where direct and concise communication from the AI assistant is preferred.

Key capabilities

  • Configuration via Appending: The skill adds configuration blocks to existing agent instruction files without overwriting them.
  • Agent-Specific Formatting: Handles different file formats (Markdown, YAML, JSON) based on the agent being configured.
  • Scope Selection: Allows users to choose between project-level and global-level configuration (where supported).
  • Truthful Communication Style: Enforces a communication style that prioritizes truthfulness, directness, and constructive criticism.

Example prompts

These are not prompts to the skill itself, but examples of interactions you might have with an agent configured by this skill:

  • "Can you review my code for potential security vulnerabilities?"
  • "I'm thinking about using X library for this task. What do you think?"
  • "Explain why my approach to solving this problem is flawed."

Tips & gotchas

  • Append Only: This skill must be appended to existing instruction files; attempting to replace them will cause issues.
  • File Location Awareness: The skill supports configuration for Claude Code, GitHub Copilot, Cursor, Windsurf, Cline, Aider, Continue.dev. Ensure the correct file location is used based on your operating system and agent.
  • Global vs. Project: Consider whether project-level or global-level configuration best suits your needs.