TokenKiller
v1.0.1Reduces token usage across multi-skill agent workflows (search, coding, debugging, testing, docs) using budgets, gating, progressive disclosure, and deduped...
⭐ 1· 242·1 current·1 all-time
byCodeRanger@buttonsinger
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (token reduction for multi-skill agents) matches the SKILL.md content: budgets, gating, progressive disclosure, and multi-skill cooperation. No unrelated binaries, env vars, or config paths are requested.
Instruction Scope
Instructions stay within the token-throttling domain (limits on reads, outputs, tool calls, L0-L3 layers). Note: it explicitly instructs the agent to ask at most 3 clarification questions and to proceed on default assumptions thereafter—this is coherent with the goal but could cause the agent to make assumptions rather than prompt the user in some cases.
Install Mechanism
Instruction-only skill with no install spec and no code files to write or execute; lowest-risk install profile.
Credentials
No environment variables, credentials, or config paths are requested. Requirements are proportional to the declared functionality.
Persistence & Privilege
Does not request always-on presence (always:false) and does not modify other skills or system settings. It can be invoked autonomously by the agent (default), which is normal for skills and not flagged alone.
Assessment
This is an instruction-only policy that appears coherent and low-risk from a supply chain/credential perspective: it asks for nothing sensitive and doesn't install code. Before enabling it, review the SKILL.md to confirm you accept its operational tradeoffs—especially that it will (a) limit reads/outputs, (b) ask at most three clarifying questions then proceed on defaults, and (c) suppress large dumps unless L3 pull scenarios or explicit user request occur. Test it on non-production workflows first to ensure the throttling rules don't cause the agent to take undesired actions or miss important clarifications. If you rely on full logs or exhaustive outputs by default, be aware TokenKiller will suppress those unless explicitly overridden.Like a lobster shell, security has layers — review code before you run it.
agentvk977xcm56v5dswg63jat79b5a982q71xbudgetvk977xcm56v5dswg63jat79b5a982q71xcostvk977xcm56v5dswg63jat79b5a982q71xdebuggingvk977xcm56v5dswg63jat79b5a982q71xdedupevk977xcm56v5dswg63jat79b5a982q71xlatestvk977xcm56v5dswg63jat79b5a982q71xprogressive-disclosurevk977xcm56v5dswg63jat79b5a982q71xsearchvk977xcm56v5dswg63jat79b5a982q71xtokensvk977xcm56v5dswg63jat79b5a982q71x
License
MIT-0
Free to use, modify, and redistribute. No attribution required.