Agent Teams Simplify And Harden
ReviewAudited by ClawScan on May 10, 2026.
Overview
The skill is a coherent code-implementation workflow, but it tells the agent to launch parallel file-editing subagents in bypass-permissions mode, which deserves careful review before use.
Install or invoke this only if you are comfortable letting multiple subagents edit your project. Run it on a separate branch, make sure the task list names the intended files and limits, keep backups or version control ready, and manually review the final diff and test results before merging or shipping.
Findings (2)
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.
A mistake or overly broad task could lead to many code files being changed automatically, potentially breaking the project or overwriting intended work.
The skill directs the assistant to create multiple agents with broad file-editing authority and bypassed permission checks. This is purpose-aligned for code implementation, but it is high-impact and not clearly bounded by per-file approval or human review before edits occur.
Spawn `general-purpose` agents (they can read, write, and edit files). One per task or one per logical group. Run them **in parallel**. ... mode: bypassPermissions
Use only on a clean branch or disposable workspace, require explicit task/file scopes, review diffs before committing, and avoid bypassPermissions unless you intentionally want unattended file edits.
It may be harder to confirm who maintains the skill or whether the install command corresponds to the reviewed artifact.
The registry metadata does not provide a source or homepage. The artifact set is instruction-only, so this is not evidence of malicious code, but it reduces provenance clarity.
Source: unknown; Homepage: none
Verify the publisher and repository path before installing, especially because the skill can direct agents to make broad code changes.