OpenClaw Cost Optimizer
v1.1.0Add cheap model aliases to your OpenRouter setup for tasks from simple to complex, cutting API costs 50-90% without changing your default model.
⭐ 11· 1.2k·3 current·3 all-time
byJeff J Hunter@jeffjhunter
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the declared requirements: the skill manipulates OpenClaw/OpenRouter model aliases, so requiring the openclaw binary and OPENROUTER_API_KEY is coherent. No unrelated service credentials or unusual binaries are requested.
Instruction Scope
SKILL.md is prescriptive: it insists on exact verbatim prompts, instructs the agent to run all setup via the exec tool, and says it will create ~/.openclaw/cost-tracker.md. This is consistent with an automation skill, but the exact-text requirements and insistence on agent-run execs mean users should review every exec approval carefully.
Install Mechanism
Instruction-only skill with no install spec or downloads. Nothing is written to disk by an installer; the only persistent artifact is the tracking file the skill creates under ~/.openclaw, which is declared in metadata.
Credentials
Only OPENROUTER_API_KEY is required (declared). That credential is necessary to configure models through OpenRouter/OpenClaw; no additional unrelated secrets or config paths are requested.
Persistence & Privilege
The skill will create ~/.openclaw/cost-tracker.md to log activity and relies on exec to run commands. always:false and normal autonomous invocation are used. This level of persistence and autonomous command-execution is reasonable for a setup/automation skill but increases the importance of reviewing each exec approval.
Assessment
This skill appears to do what it says: add model aliases via the OpenClaw CLI and log savings in ~/.openclaw/cost-tracker.md. Before installing: 1) Verify the openclaw binary on your system is from a trusted source; the skill relies on that CLI to change your model aliases. 2) Keep your OPENROUTER_API_KEY limited in scope if possible; the skill will use it to configure models. 3) When the agent presents exec approvals, inspect the exact commands it will run before approving — the SKILL.md enforces that the agent run commands automatically. 4) Back up your existing OpenClaw/OpenRouter configuration so you can revert if needed. 5) If you want extra caution, test the process in a non-production/staging environment first. The skill's strict verbatim prompts and exec-first behavior are unusual but not inherently malicious; they just increase the need for the user to review each automated action.Like a lobster shell, security has layers — review code before you run it.
advisorvk978pv1qy28gv6mnmz04wy06y5814p8nai-personavk978pv1qy28gv6mnmz04wy06y5814p8nambient-monitoringvk978pv1qy28gv6mnmz04wy06y5814p8ncontext-protectionvk978pv1qy28gv6mnmz04wy06y5814p8ncost-savingvk978pv1qy28gv6mnmz04wy06y5814p8nescalationvk978pv1qy28gv6mnmz04wy06y5814p8nframeworkvk978pv1qy28gv6mnmz04wy06y5814p8nheartbeatvk978pv1qy28gv6mnmz04wy06y5814p8nin-chat-commandsvk978pv1qy28gv6mnmz04wy06y5814p8nlatestvk978pv1qy28gv6mnmz04wy06y5814p8nmemoryvk978pv1qy28gv6mnmz04wy06y5814p8nnever-forgetvk978pv1qy28gv6mnmz04wy06y5814p8npresetsvk978pv1qy28gv6mnmz04wy06y5814p8nproductionvk978pv1qy28gv6mnmz04wy06y5814p8nreliable-agentvk978pv1qy28gv6mnmz04wy06y5814p8nsecurityvk978pv1qy28gv6mnmz04wy06y5814p8nsetup-wizardvk978pv1qy28gv6mnmz04wy06y5814p8nstarter-packsvk978pv1qy28gv6mnmz04wy06y5814p8nteamvk978pv1qy28gv6mnmz04wy06y5814p8nworkspacevk978pv1qy28gv6mnmz04wy06y5814p8nzero-terminalvk978pv1qy28gv6mnmz04wy06y5814p8n
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
💰 Clawdis
Binsopenclaw
EnvOPENROUTER_API_KEY