Skip to content
TrustedSkillsbeta
Back to all skills

Cass

Listed
dicklesworthstone·vlatest·ai-ml

Cass generates creative story prompts and ideas to overcome writer’s block and spark your imagination for writing projects.

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 dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations --skill cass -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

dicklesworthstone

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 failed 1 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No credential access: failed

    Touches credential material in 1 place.

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

    What it found

    • skills/cass/SKILL.md:286SSH private keys or config
      cass sources setup                                      # interactive wizard, auto-discovers from ~/.ssh/config

  • 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

    Only contacts known or declared hosts: github.com.

    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.

    Hosts contacted

    github.comsource host

  • 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 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 dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations at 4d332440c3.

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

Commit
4d332440c3
Manifest
skills/cass/SKILL.md
Scanned
23 files, 4,300 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

This skill, Cass, provides a unified command-line interface (CLI) and text user interface (TUI) to index and search through your local history of coding agent sessions. It aggregates data from 11 different agents including Codex, Claude Code, Gemini CLI, Cline, OpenCode, Amp, Cursor, ChatGPT, Aider, Pi-Agent, and Factory (Droid). Cass is designed for AI agents and requires the --robot or --json flags to function correctly within an automated workflow.

When to use it

  • Troubleshooting coding errors: Search across all your agent sessions to find previous attempts at solving a similar problem.
  • Knowledge transfer between agents: Identify patterns, solutions, and approaches used by different AI coding assistants.
  • Understanding agent behavior: Analyze session data to understand how various agents respond to specific prompts or code challenges.
  • Discovering capabilities of coding agents: Use cass capabilities to explore the features offered by each integrated agent.

Key capabilities

  • Cross-agent search: Searches sessions from 11 different coding AI agents.
  • JSON output for automation: Provides machine-readable JSON output via --robot or --json flags.
  • Metadata retrieval: Allows searching with metadata like elapsed time, cache statistics and freshness information.
  • Session viewing & expansion: View specific lines of code within sessions and expand the surrounding context.
  • Health checks and index rebuilding: Provides commands to verify the health of the index and rebuild it if necessary.

Example prompts

  • cass search "authentication error" --robot --limit 5 - Searches for sessions containing "authentication error" and returns the top 5 results in JSON format.
  • cass view /path/to/session.jsonl -n 42 --json - Views a specific session file at line number 42, outputting the result as JSON.
  • cass capabilities --json - Lists the supported capabilities of the integrated coding agents in JSON format.

Tips & gotchas

  • Robot Mode Required: Always use the --robot or --json flags when using Cass within an AI agent to prevent blocking the terminal with the interactive TUI.
  • Index Maintenance: Regularly check the health of the index (cass health) and rebuild it if needed (cass index --full).
  • JSON Output is Key: For automated workflows, rely on the --robot or --json flags to ensure machine-readable output.