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.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

The canonical home for this skill is model-usage in Hung-Reo/hungreo-openclaw

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplary concise, action-first skill body: executable commands for every common case, unambiguous single-action workflow, and a verified, well-signaled one-level-deep reference. The only trimming opportunity is the developer-facing TODO note.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence ("Uses the most recent daily row with modelBreakdowns", "Values are cost-only per model"), with no explanations of concepts Claude already knows. It is not a 5 because the developer-facing line "TODO: add Linux CLI support guidance once CodexBar CLI install path is documented for Linux" is a token that does not earn its place for the executing model.	4 / 5
Actionability	The Quick start and Inputs sections give copy-paste-ready commands covering the common cases (current/all modes, both providers, JSON output, file and stdin input), e.g. "python {baseDir}/scripts/model_usage.py --provider claude --mode all --format json --pretty". Not a 4 because the examples are fully executable and span the realistic invocation space.	5 / 5
Workflow Clarity	This is a simple, single-purpose read-only skill and the two-step quick start ("1. Fetch cost JSON... 2. Use the bundled script to summarize by model") backed by exact commands is unambiguous; the Current model logic section even documents fallback behavior. No destructive or batch operation exists, so no validation checkpoint cap applies.	5 / 5
Progressive Disclosure	The ~45-line body is well organized into Overview/Quick start/Inputs/Output/References, and the single reference "Read `references/codexbar-cli.md` for CLI flags and cost JSON fields" is clearly signaled, purpose-stated, one level deep, and verified to exist in the bundle. Not a 4 because there is no misplaced inline content and navigation is trivial.	5 / 5
	Total	19 / 20 Passed

Description

82%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with an explicit trigger clause, concrete capability list, and a distinct tool-specific niche. Its main weaknesses are the second-person "when you need" phrasing (voice penalty) and slightly thin synonym coverage for natural user phrasings.

Suggestions

Rewrite the second clause in third person to match the rubric's voice requirement, e.g. "Trigger when the user asks for model-level usage or cost data from codexbar, or when a scriptable per-model summary of codexbar cost JSON is needed."

Add natural synonyms users might say, such as "spending", "model spend", or "which model", to broaden trigger-term coverage.

Mention the output forms (text summary or JSON) in the capability list so the 'what' is fully comprehensive.

Dimension	Reasoning	Score
Specificity	"summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown" lists several concrete actions (would be a 4), but the second-person clause "when you need a scriptable per-model summary" triggers the rubric's voice penalty, reducing the score by 1. It is not a 2 because the domain and actions are concrete and specific, far beyond "names the domain but actions are minimal".	3 / 5
Completeness	The description explicitly answers both: what ("summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown") and when ("Trigger when asked for model-level usage/cost data from codexbar"). Not a 4 because the trigger guidance is explicit and concrete rather than merely present-but-imprecise.	5 / 5
Trigger Term Quality	"model-level usage/cost data", "per-model summary", and repeated "codexbar" give good keyword coverage matching what a user would naturally say. It falls short of a 5 because natural synonyms and variations like "spending", "which model", or "model spend" are missing.	4 / 5
Distinctiveness Conflict Risk	It names a specific tool ("CodexBar CLI", "codexbar cost JSON") with tool-scoped triggers, giving it a clear niche with minimal conflict risk against generic usage/analysis skills. Not a 4 because every trigger is anchored to the codexbar tool rather than a broad domain.	5 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 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	14 / 16 Passed

Repository: Bitterbot-AI/bitterbot-desktop
Path: skills/model-usage/SKILL.md
Commit: 1c7dc1b

Reviewed: 20 hours ago

Table of Contents

Discovery Implementation Validation

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.