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.
91
88%
Does it follow best practices?
Impact
100%
3.70xAverage score across 3 eval scenarios
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 its niche (CodexBar CLI cost data) and provides explicit trigger guidance. The 'when' clause is well-articulated with natural keywords. The main weakness is that the specific capabilities could be more granular—listing concrete output formats or operations beyond 'summarize'.
Suggestions
Add more specific concrete actions such as 'parse codexbar cost JSON', 'generate per-model cost tables', or 'compare spending across models' to strengthen the specificity dimension.
| 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 tables', or 'compare costs across models'. | 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 summaries. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche—CodexBar CLI cost usage with per-model breakdowns. The combination of 'codexbar', 'cost JSON', and 'per-model summary' makes it highly unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
87%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 explanations of the current-model selection logic. Its main weakness is the lack of error handling or validation guidance—there's no mention of what to do when commands fail, JSON is malformed, or the provider flag is wrong. The progressive disclosure and token efficiency are excellent.
Suggestions
Add brief error handling guidance: what does the script output when codexbar is not found, JSON is invalid, or no model breakdowns exist?
Consider adding a validation step or expected output snippet so Claude can verify the command succeeded before presenting results to the user.
| 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. The skill assumes Claude's competence throughout. | 3 / 3 |
Actionability | Provides fully executable CLI commands with concrete flags and options. The examples cover multiple modes (current, all, json output) and multiple input methods (CLI, file, stdin), all copy-paste ready. | 3 / 3 |
Workflow Clarity | The quick start provides a basic two-step sequence, and the 'Current model logic' section explains fallback behavior clearly. However, there are no validation checkpoints or error handling guidance—what happens if codexbar isn't installed, the JSON is malformed, or the provider is invalid? | 2 / 3 |
Progressive Disclosure | Content is well-organized into clear sections (Quick start, Current model logic, Inputs, Output) with a single-level reference to codexbar-cli.md for CLI details. Appropriate split between overview and reference material. | 3 / 3 |
Total | 11 / 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
- trpc-group/trpc-agent-go
- Commit
09cce3e
- 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.