Add cheap model aliases to your OpenRouter setup for tasks from simple to complex, cutting API costs 50-90% without changing your default model.
Security Analysis
high confidenceThe skill's requirements and instructions align with its stated purpose: it needs the OpenClaw CLI and an OpenRouter API key to add model aliases and log savings; nothing requested appears unrelated or excessive.
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.
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.
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.
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.
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.
Guidance
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.
Latest Release
v1.1.0
Cut your OpenRouter API costs 50-90%. Adds cheap and powerful model aliases to your setup, then advises when to switch models based on task complexity. 8 presets, 29 models, zero config risk — only adds aliases, never changes your default. 3 clicks to set up. Built by Jeff J Hunter. Changelog v1.1.0 — Cost Tracker, Mix & Match, Monthly Calculator 💸 Cost Tracker: agent logs model switches, "how much have I saved?" shows running total with monthly projection 🔀 Mix & Match: build custom presets by picking one model per tier from the full 29-model registry 📊 Monthly Cost Calculator: "estimate my monthly costs" compares default vs. optimized spending Author branding and links added Security fix from v1.0.1 included v1.0.1 — Security Fix Removed insecure fallback that accepted API keys via chat Agent now always uses OpenClaw's native auth wizard (openclaw models auth add) Added OPENROUTER_API_KEY to required env in metadata v1.0.0 — Initial Release 8 presets: balanced, code-machine, claude-diehards, big-context, openai-focused, tool-master, ultra-budget, free-tier 29 verified OpenRouter models with aliases, pricing, and strengths Smart Cost Advisor suggests model switches based on task complexity Additive only — never changes default model, fallbacks, or existing config Uses OpenClaw's native openclaw models aliases add — no custom scripts Setup: 3 Approve clicks, zero terminal usage Advisor on/off toggle Easy undo: just remove aliases
More by @jeffjhunter
Published by @jeffjhunter on ClawHub
