skill-candidates/model-usage/SKILL.md
Summarize per-model usage cost from local CodexBar cost JSON. Use when you need current-model or all-model cost breakdowns for Codex or Claude usage.
npx skillsauth add grtninja/skill-arbiter model-usageInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill to report model-level usage cost from local CodexBar data.
codexbar cost --format json or from a saved JSON file.current for the most recent model signal, or all for aggregate breakdown.usage-watcher and skill-cost-credit-governor when needed.python3 "$CODEX_HOME/skills/model-usage/scripts/model_usage.py" \
--provider codex \
--mode current
python3 "$CODEX_HOME/skills/model-usage/scripts/model_usage.py" \
--provider codex \
--mode all \
--format json \
--pretty
python3 "$CODEX_HOME/skills/model-usage/scripts/model_usage.py" \
--provider claude \
--input /tmp/codexbar-cost.json \
--mode all
.tmp/ for reproducible review.Use this skill only for model-level usage summarization.
Do not use this skill for billing exports, payment actions, or account mutation.
references/codexbar-cli.mdtools
Run a defender-first security sweep on code, configs, prompts, model/tooling surfaces, or third-party contribution lanes. Use when a request involves safe bug, leak, zero-day-class, exploit, or hack hunting for protection, when contributing to outside repositories and you want a focused security pass, or when touching auth, secrets, permissions, network exposure, prompt/tool boundaries, data flow, or update/build surfaces. This skill is defensive only and must never be used for weaponization or unauthorized access.
development
Validate and repair VRM Sandbox startup acceptance with shim-first local model authority, frontend/backend bring-up, and avatar-runtime launch proof. Use when launch behavior, chat handoff, voice fallback, or runtime bridge acceptance must be verified end to end.
documentation
Align documented voice-command catalogs, endpoint action allowances, and live runtime handlers so operator-visible voice surfaces match what the stack can actually execute. Use when voice command docs, parser matrices, endpoint permissions, or runtime action routing drift apart.
development
Track SkillHub trend and topic drift, maintain a bounded rewrite watchlist, and surface emerging gaps worth turning into repo-owned skills. Use when the marketplace query set shows new families or when the current shortlist has gone stale.