CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/context-budget/SKILL.md

The canonical home for this skill is tdg-personal/context-budget

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The content is well-structured and highly actionable with concrete thresholds and an output template, but it lacks explicit validation checkpoints in its workflow and carries some tightening opportunity in the report template and examples.

Suggestions

Add an explicit validation step, e.g. after Inventory: "Reconcile estimated total against the live /context or token-count output before classifying, and re-check after any proposed removal."

Tighten the Examples section to one representative example and reference the report template once instead of reproducing a full ASCII table plus three scenarios.

Optionally move the verbose-mode per-file breakdown details into a reference file so the main SKILL.md stays a lean overview.

DimensionReasoningScore

Conciseness

The body is dense and avoids explaining concepts Claude already knows, but the full ASCII report template plus three worked examples and the verbose-mode description could be tightened, fitting the "mostly efficient but could be tightened" anchor rather than the every-token-earns-its-place anchor at 3.

2 / 3

Actionability

Concrete, specific guidance throughout — exact thresholds (>200 lines, >400 lines, >30-word descriptions, ~500 tokens/tool, words × 1.3), named directories (agents/*.md, skills/*/SKILL.md, .mcp.json), explicit bucketing criteria, and a copy-paste-ready report template — which the instruction-only scoring note protects despite the absence of executable code, so it is not the incomplete/pseudocode anchor at 2.

3 / 3

Workflow Clarity

The four phases (Inventory → Classify → Detect Issues → Report) give a clear sequence, but there are no explicit validation or verification checkpoints (e.g., reconciling estimates against actual /context output), matching the "sequence present but checkpoints missing or implicit" anchor at 2 rather than the validation-with-feedback-loops anchor at 3.

2 / 3

Progressive Disclosure

No bundle files exist and the body references none, so there are no dangling or deeply nested references; the single self-contained file is organized into clear, well-signaled sections (When to Use, How It Works phases, Examples, Best Practices), matching the well-organized overview anchor at 3.

3 / 3

Total

10

/

12

Passed

Description

67%

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

The description is specific and occupies a clear niche, but it omits any explicit "Use when..." trigger guidance and relies on technical phrasing rather than natural user terms, capping completeness and trigger-term quality at 2.

Suggestions

Add an explicit trigger clause, e.g. "Use when the session feels sluggish, context is filling up, or before adding new agents/skills/MCP servers to check headroom."

Mirror natural user phrasing in the trigger terms ("context is full", "running out of context", "too many MCP servers") rather than only technical terms like "consumption" and "bloat".

Keep the concrete action list but pair it with the when-to-use clause so both "what" and "when" are explicit.

DimensionReasoningScore

Specificity

Lists several concrete actions ("Audits...consumption across agents, skills, MCP servers, and rules", "Identifies bloat, redundant components", "produces prioritized token-savings recommendations") and names the target components, matching the multiple-specific-actions anchor rather than the partial domain-only anchor at 2.

3 / 3

Completeness

It clearly answers "what" but provides no "Use when..." clause or equivalent explicit trigger guidance for when Claude should invoke it, which per the guidelines caps completeness at 2 rather than 3.

2 / 3

Trigger Term Quality

Relevant domain keywords appear ("context window", "bloat", "token-savings") but the phrasing is technical rather than the natural terms a user would say (e.g. "context is full", "running out of context", "too many MCP servers"), so it sits at "some relevant keywords, missing common variations" and not the full natural-coverage anchor at 3.

2 / 3

Distinctiveness Conflict Risk

Context-window/token-overhead auditing is a narrow, distinctive niche unlikely to be claimed by another skill, matching the clear-niche anchor; it is not the somewhat-generic "could overlap" case at 2.

3 / 3

Total

10

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
affaan-m/ECC
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.