ClawHub

Low Token Usage

v1.0.0

Optimizes for minimal token usage. Removes fluff, eliminates step-by-step narration, and delivers results-only communication.

⭐ 0· 212·1 current·1 all-time
by@tooled-app
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name, description, and runtime instructions align: the skill's rules and examples explicitly aim to reduce token use. No unrelated capabilities, env vars, or binaries are requested.
ℹ
Instruction Scope
SKILL.md stays within its stated goal (remove narration, be concise). One implementation detail is ambiguous: the 'Activation' section claims auto-activation on token >75% or keywords — that depends on the host agent/platform, not the skill itself. Also, the rule to 'complete the task, then present final result' intentionally omits intermediate reasoning, which is coherent with the stated purpose but may reduce auditability or make debugging harder.
✓
Install Mechanism
Instruction-only skill with no install spec and no code files — minimal footprint and no archive or external downloads.
✓
Credentials
No environment variables, credentials, or config paths are requested; nothing disproportionate to the stated purpose.
ℹ
Persistence & Privilege
always:false (no forced global presence). The skill allows autonomous invocation (disable-model-invocation:false), which is platform-default — not a flaw by itself but worth noting because the agent could choose to apply the concise style automatically when eligible.
Assessment
This skill simply tells the agent to be terse and avoid step-by-step narration; it does not request credentials or install code. Before enabling, decide whether you are comfortable losing intermediate reasoning and verbose explanations (useful for debugging, audits, or pedagogy). Also confirm how your platform decides auto-activation (keyword triggers or token thresholds) and whether you can disable the skill if you want full explanations later.

Like a lobster shell, security has layers — review code before you run it.

latestvk97dq1wry0n8jtfcgf3g0fkyp982r3qn

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments