ClawGator Superpowers
PassAudited by VirusTotal on May 12, 2026.
Overview
Package: ClawGator Superpowers (mcp) Version: 1.0.0 Description: Framework pengembangan perangkat lunak lengkap untuk tim ClawGator. Brainstorming, planning, eksekusi sistematis, TDD, debugging, code review, dan git worktrees. The 'ClawGator Superpowers' package provides a comprehensive set of AI agent skills and supporting utilities designed for software development workflows, including brainstorming, planning, test-driven development (TDD), systematic debugging, code review, and Git worktree management. The package consists primarily of Markdown files defining AI agent 'skills' (workflows and best practices), along with several executable scripts and a core JavaScript module. Executable components include: - `hooks/session-start.sh`: A shell script that runs on session start to inject context, read skill documentation, and check for legacy configuration. It uses standard shell commands and file I/O, including a robust JSON escaping function. - `skills/systematic-debugging/find-polluter.sh`: A diagnostic shell script to identify which test creates unwanted files or state by running `npm test` on individual test files. This is a legitimate debugging tool for developers. - `skills/writing-skills/render-graphs.js`: A Node.js script that renders Graphviz DOT diagrams from Markdown files into SVG images, executing the `dot` command. This is a benign utility for documentation visualization. - `lib/skills-core.js`: A Node.js module providing core functionalities for skill management, such as parsing frontmatter, discovering skills, resolving skill paths, and checking for Git repository updates using `git fetch` and `git status`. These operations are standard for a self-managing plugin. The `openclaw.plugin.json` manifest defines the plugin's configuration and a set of high-level tools for AI agent interaction, consistent with a development workflow. Documentation files (`.md`) describe the skills, installation, usage, and internal design/testing processes. The `docs/windows/polyglot-hooks.md` explains a cross-platform technique for shell scripts, which is a legitimate compatibility solution. All observed code logic and operations are consistent with the stated purpose of enhancing a developer's workflow within an IDE/agent environment. There are no indications of malicious activities such as unauthorized data access, exfiltration, system compromise, or obfuscation. The package focuses on structured development practices and diagnostic tools.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The skill can steer future sessions automatically, including resumed or cleared sessions.
The skill registers an asynchronous command hook that runs on session lifecycle events, giving it persistent behavior even when the user has not explicitly invoked the skill.
"SessionStart": [{ "matcher": "startup|resume|clear|compact", ... "command": "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh", "async": true }]Make the session-start hook opt-in, disclose it prominently in metadata and documentation, and provide a simple way to disable it.
The agent may force this workflow into tasks where the user expected a quick answer or a different approach.
This instruction is overbroad and makes the skill's own invocation rule authoritative across many situations, which can override narrower user intent.
"If you think there is even a 1% chance a skill might apply, you ABSOLUTELY MUST invoke it"
Scope invocation to clearly defined development tasks and avoid absolute self-invocation language.
Installing the skill may cause local code to run at session start, not just provide passive instructions.
The package contains a hook that executes a shell script automatically, while the registry describes the package as having no install spec and being instruction-only.
"type": "command", "command": "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh"Declare the hook and command execution in metadata, document exactly what the script does, and require explicit user consent before enabling it.
A mistaken or premature action could change or discard code work.
The skill declares tools that can affect repository state, including merging or discarding a branch. This is purpose-aligned for a development workflow but high-impact.
"finish_development_branch": ... "enum": ["merge", "pr", "keep", "discard"]
Require explicit user confirmation before merge, PR creation, discard, or other repository-mutating actions.
Users have less information to verify where the code came from or whether it matches an upstream project.
The registry provenance is incomplete for a package that includes runnable code and hooks.
Source: unknown; Homepage: none; Install specifications: No install spec — this is an instruction-only skill.
Verify the package source before installing and prefer a version with a public repository, pinned provenance, and accurate install metadata.
Project context or code may be shared among subagents more broadly than the user expects.
The workflow includes subagents and parallel agents, but the provided top-level artifacts do not define detailed data-sharing or permission boundaries for those agents.
"SUBAGENT-DRIVEN DEV" ... "Fresh subagent per task"
Review subagent prompts and limit what files, secrets, and project context are passed to subagents.