token-efficient-task-router
AdvisoryAudited by Static analysis on May 2, 2026.
Overview
No suspicious patterns detected.
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 agent may ask more clarifying questions, shorten outputs, or delay broad work until the user confirms scope.
This intentionally changes how the agent approaches tasks before acting. It is broad behavior control, but it is clearly disclosed and matches the skill’s stated purpose.
Before executing any user request, classify the task by clarity, complexity, risk, and expected token cost. Route the task to Ask, Plan, Craft, or Expert mode.
Use this skill when you want cost-conscious routing and confirmation gates; disable or avoid invoking it for simple tasks where you want a direct answer.
There is no artifact-backed evidence of credential use, but the metadata inconsistency is worth noticing before installation.
The capability signal suggests sensitive credential relevance, but the declared credential requirements are empty and the visible skill text does not request credential access.
Capability signals: requires-sensitive-credentials; Required env vars: none; Primary credential: none
Do not provide API keys, cookies, sessions, or other credentials to this skill unless a future version clearly explains why they are needed.
Installing the skill appears low-risk, but manually running included scripts would require separate trust in the package source.
The package has limited provenance metadata and includes script files, although no install specification indicates automatic execution.
Source: unknown; Homepage: none; No install spec — this is an instruction-only skill; Code file presence: scripts/package_skill.py, scripts/validate_skill.py
Install through ClawHub when possible and inspect any included scripts before running them manually.