model-usage
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
86
84%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description that clearly identifies a narrow, specific tool (CodexBar CLI) and provides explicit trigger guidance. Its main weakness is that the 'what' portion could enumerate more concrete actions beyond 'summarize per-model usage.' The trigger terms and completeness are strong, making it easy for Claude to select this skill appropriately.
Suggestions
Add more specific concrete actions such as 'parse codexbar cost JSON output', 'calculate total spend per model', or 'generate cost comparison tables' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (CodexBar CLI cost usage) and describes some actions (summarize per-model usage, current model or full model breakdown), but the concrete actions are somewhat limited—it doesn't list specific operations like 'parse JSON output', 'generate cost reports', or 'compare model costs'. | 2 / 3 |
Completeness | Clearly answers both 'what' (summarize per-model usage for Codex or Claude, including current model or full breakdown) and 'when' (explicit trigger clause: 'Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'codexbar', 'per-model usage', 'cost data', 'model-level usage', 'cost JSON', 'model breakdown', 'Codex', 'Claude'. These cover the terms a user would naturally use when asking about CLI cost tracking. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive—targets a very specific tool (CodexBar CLI) and a specific use case (per-model cost/usage summaries). Unlikely to conflict with other skills due to the narrow niche of codexbar cost JSON processing. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, concise skill that provides actionable CLI commands and clear input/output documentation. Its main weaknesses are the lack of error handling/validation guidance in the workflow and the inability to verify referenced bundle files. The content efficiently communicates what's needed without over-explaining.
Suggestions
Add error handling guidance: what to do if codexbar CLI is not found, if JSON is malformed, or if no modelBreakdowns exist for any day.
Ensure bundle files (scripts/model_usage.py, references/codexbar-cli.md) are actually provided so references can be verified and progressive disclosure is functional.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Every section serves a purpose, there's no explanation of basic concepts, and the TODO note is appropriately brief. No unnecessary padding or explanation of things Claude already knows. | 3 / 3 |
Actionability | Provides fully executable CLI commands with concrete flags and options. The quick start, input examples, and output format options are all copy-paste ready with specific provider/mode combinations demonstrated. | 3 / 3 |
Workflow Clarity | The steps are listed (fetch JSON, run script) but there's no validation or error handling guidance. What happens if codexbar CLI isn't installed? What if the JSON is malformed? No feedback loops for common failure modes. | 2 / 3 |
Progressive Disclosure | References a bundled script and a references file, but no bundle files were provided to verify these exist. The reference to `references/codexbar-cli.md` is a good signal, but the overall structure is slightly flat — the 'Current model logic' section could arguably be in a reference file rather than inline. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
- Repository
- deepgram/dglabs-deepclaw
- Commit
ec8d4f8
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.