ctx-stats

Show how much context window context-mode saved this session. Displays token consumption, context savings ratio, and per-tool breakdown. Read-only — shows stats only, no reset capability. To wipe the knowledge base entirely, use ctx_purge instead. Trigger: /context-mode:ctx-stats

Quality

92%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Critical

Do not install without reviewing

Quality

Content

100%

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-crafted, concise skill that clearly instructs Claude on a single task: calling a stats tool and displaying its full output. The CRITICAL instruction about not summarizing the output is a valuable guardrail that addresses a known Claude behavior. The brief mention of the related purge command provides useful context without bloating the skill.

Dimension	Reasoning	Score
Conciseness	The skill is lean and efficient. Every line serves a purpose — tool call, output formatting rule, and a brief note on the related purge command. No unnecessary explanations of what stats are or how MCP tools work.	3 / 3
Actionability	Provides a specific MCP tool name to call, explicit instructions on how to handle the output (copy-paste entirely), and concrete example sentences for the summary line. Claude knows exactly what to do.	3 / 3
Workflow Clarity	This is a simple, single-purpose skill (call tool, display output, add one sentence). The three steps are clearly sequenced and unambiguous. The CRITICAL formatting constraint acts as a validation checkpoint for output quality.	3 / 3
Progressive Disclosure	For a simple skill under 50 lines with no need for external references, the content is well-organized with clear sections (Instructions, Purge). The cross-reference to ctx_purge is appropriately brief and one level deep.	3 / 3
	Total	12 / 12 Passed

Description

85%

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 well-structured description that clearly communicates what the skill does (display context window statistics) and when to use it (via explicit trigger). It effectively differentiates itself from the related ctx_purge skill. The main weakness is that trigger terms could include more natural language variations users might say when looking for usage statistics.

Suggestions

Add natural language trigger terms users might say, such as 'token usage', 'how much context', 'memory stats', or 'usage statistics' to improve discoverability beyond the slash command.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: showing context window savings, displaying token consumption, context savings ratio, and per-tool breakdown. Also clarifies what it does NOT do (no reset capability).	3 / 3
Completeness	Clearly answers 'what' (shows token consumption, context savings ratio, per-tool breakdown) and 'when' (explicit trigger command '/context-mode:ctx-stats'). Also distinguishes from related skill ctx_purge, providing clear guidance on when to use each.	3 / 3
Trigger Term Quality	Includes some relevant terms like 'token consumption', 'context savings', 'context window', and the explicit trigger '/context-mode:ctx-stats', but lacks natural user language variations like 'how much context am I using', 'token usage', 'stats', or 'memory usage'.	2 / 3
Distinctiveness Conflict Risk	Very distinct niche with a specific trigger command. Explicitly differentiates from ctx_purge, making it clear this is read-only stats display. Unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: mksglu/context-mode
Commit: e174272

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.