Loop

PassAudited by ClawScan on May 1, 2026.

Overview

This instruction-only skill is coherent and bounded, but users should understand it can run repeated agent attempts and store loop history under ~/loop.

This skill appears safe for controlled iterative work when you provide clear success criteria and limits. Before installing or using it, decide what files or commands the agent may touch, require explicit approval for destructive actions, and remember that loop history may be saved locally in ~/loop/.

Findings (3)

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.

What this means

The agent may continue working through multiple attempts without a new prompt each time, up to the configured limit.

Why it was flagged

The skill intentionally enables autonomous repeated attempts, but it discloses that behavior and sets a hard stopping limit.

Skill content
Runs iterative attempts toward defined success criteria ... NEVER runs indefinitely (max 10 iterations hard limit)
Recommendation

Use it only with clear success criteria, set an appropriate max iteration count, and monitor actions that could affect important files or systems.

What this means

A badly scoped task or unsafe verification command could be repeated across iterations.

Why it was flagged

The loop can lead the agent to repeatedly perform task actions and run verification commands, which is purpose-aligned but can amplify mistakes if the task is scoped poorly.

Skill content
Execute — Attempt the task ... Verify — Check success criteria ... Verify command | Recommended | `npm test`
Recommendation

Provide narrow task instructions, review any command before use, and require explicit approval for destructive or high-impact actions.

What this means

Task details or lessons from prior loops may be reused later, and sensitive information could be stored if included in loop summaries.

Why it was flagged

The skill persists loop state and learnings locally, including optional cross-loop patterns that may influence future iterations.

Skill content
All loop data stored in ~/loop/: active.json ... history/{id}.json ... learnings.md — Cross-loop patterns (optional)
Recommendation

Avoid including secrets or sensitive data in loop logs, and periodically review or delete ~/loop/ if persistence is no longer wanted.