context-budget

Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations. Use when the context window is filling up too fast and the agents, skills, MCP servers, or rules consuming it need to be identified.

Quality

83%

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 tdg-personal/context-budget

Quality

Content

75%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-structured, actionable audit skill with a clear phased workflow and concrete thresholds/formulas. Trimming the redundant intro and splitting the report template or verbose-mode details into a reference file would push conciseness and progressive disclosure higher.

Suggestions

Remove or compress the opening 'Analyze token overhead...' line since it duplicates the frontmatter description.

Move the verbose-mode per-file breakdown and the full ASCII report template into a references/ file (e.g. REPORT_TEMPLATE.md) and link to it, keeping the body as an overview.

Add a short validation/checklist step in Phase 4 (e.g. 're-sum flagged tokens to confirm the reported savings total') to give the workflow an explicit feedback loop.

Dimension	Reasoning	Score
Conciseness	Mostly lean — tight tables, numeric thresholds, and a copy-paste report template — but the opening line 'Analyze token overhead across every loaded component... to reclaim context space' largely restates the frontmatter description.	4 / 5
Actionability	Gives concrete, executable guidance: token formulas (words × 1.3, chars / 4), flagging thresholds (>200 lines, >30 words, >400 lines), file globs (agents/.md, skills//SKILL.md), and a filled-out report template; lacks a single runnable command, appropriate for an audit skill.	4 / 5
Workflow Clarity	Clear four-phase sequence (Inventory → Classify → Detect Issues → Report) with explicit per-component criteria; being a read-only audit it needs no validation checkpoints, though error-recovery loops are absent.	4 / 5
Progressive Disclosure	Well-organized into labeled sections (When to Use, How It Works, Examples, Best Practices) and self-contained with no external references needed; at ~130 lines it is somewhat long for a single file but appropriately structured.	4 / 5
	Total	16 / 20 Passed

Description

92%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, specific description with concrete actions and an explicit 'Use when' trigger tied to context-window pressure. Slightly richer trigger-term synonyms (e.g. 'running out of context', 'context headroom') would make it fully comprehensive.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Audits Claude Code context window consumption', 'Identifies bloat, redundant components', 'produces prioritized token-savings recommendations' — across a comprehensive set of components (agents, skills, MCP servers, rules).	5 / 5
Completeness	Explicitly answers both what ('Audits... consumption', 'Identifies bloat', 'produces prioritized... recommendations') and when ('Use when the context window is filling up too fast and the agents, skills, MCP servers, or rules consuming it need to be identified').	5 / 5
Trigger Term Quality	Includes the natural phrase 'context window is filling up too fast' alongside 'context window' and 'token-savings', but omits common synonyms like 'running out of context', 'too many tokens', or 'context headroom'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (context-window budget auditing) with a distinct trigger ('context window is filling up too fast') that is unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 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/context-budget/SKILL.md
Commit: 06c5e11

Reviewed: 3 days 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.