cost-tracking

Track and report Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log. Use when the user asks about costs, spending, usage, tokens, budgets, or cost breakdowns by model, session, or date.

Quality

82%

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

Quality

Content

81%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.

A well-crafted, highly actionable skill body: executable node examples, an explicit validation checkpoint for the missing-log case, and an anti-patterns section that guards the key correctness trap (double-counting cumulative rows). Its weaknesses are the over-detailed internal-cache paragraph and the lack of concrete code for the CSV/drilldown variants it advertises.

Dimension	Reasoning	Score
Conciseness	Mostly lean and instructive, but the ~/.claude/metrics/cost-snapshots/ cache paragraph (30-day pruning, 512-session cap, 16 MiB catch-up, 1 MiB malformed-row handling) is internal tracker detail that the skill itself says is not used for reports and could be trimmed.	4 / 5
Actionability	Fully executable copy-paste node snippets for the existence check and the summary-by-model report, including missing-log handling; minor gap is that session drilldown and CSV export are only described ('iterate the same latest set') without concrete code.	4 / 5
Workflow Clarity	The read-only single-purpose task is unambiguous with a clear sequence: verify the log exists (explicit checkpoint), do not fabricate data when missing, dedupe to the latest row per session, then report; anti-patterns reinforce the critical correctness steps.	5 / 5
Progressive Disclosure	No bundle files exist and the single ~107-line SKILL.md is well organized with clear section headers, all content appropriately placed; it sits above the under-50-line simple-skill allowance and the cache-internals detail is a candidate for a split-out reference.	4 / 5
	Total	17 / 20 Passed

Description

83%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: it states a concrete capability set tied to a specific data source and pairs it with an explicit, well-scoped 'Use when' trigger clause. The main improvement would be broadening natural trigger phrases to include user-style questions like 'how much have I spent'.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete capabilities ('Track and report Claude Code token usage, spending, and budgets... cost breakdowns by model, session, or date'), but minor gaps such as CSV export and per-session summaries keep it below comprehensive.	4 / 5
Completeness	Explicitly answers both what ('Track and report Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log') and when ('Use when the user asks about costs, spending, usage, tokens, budgets, or cost breakdowns by model, session, or date') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Good natural keyword coverage with synonyms ('costs, spending, usage, tokens, budgets'), but a few natural user phrases like 'how much have I spent' are absent.	4 / 5
Distinctiveness Conflict Risk	The named ECC cost-tracker metrics log gives it a clear niche, but broad triggers like 'tokens', 'usage', and 'budgets' create minor overlap risk with token-budgeting and context-planning skills.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/cost-tracking/SKILL.md
Commit: c70874f

Reviewed: 1 day 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.