.cursor/skills/CRUX-Utils/SKILL.md
Multi-purpose utility for CRUX compression workflows. Provides token estimation and checksum calculation. Use when estimating tokens for compression, comparing file sizes, or getting checksums for sourceChecksum tracking.
npx skillsauth add zotoio/x-fidelity CRUX-UtilsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Multi-purpose utility for CRUX compression workflows. Provides deterministic tools for token estimation and checksum calculation.
# Token count estimation
bash .cursor/skills/CRUX-Utils/scripts/crux-utils.sh --token-count <file>
# Compare source vs CRUX (ratio mode)
bash .cursor/skills/CRUX-Utils/scripts/crux-utils.sh --token-count --ratio <source> <crux>
# Get checksum for sourceChecksum frontmatter
bash .cursor/skills/CRUX-Utils/scripts/crux-utils.sh --cksum <file>
--token-count <file>Estimate token count for a single file.
Output:
=== Token Estimate: example.md ===
Prose tokens: 397
Code tokens: 0
Special tokens: 0
---
TOTAL TOKENS: 397
--token-count --ratio <source> <crux>Compare source file vs CRUX file and calculate compression ratio.
Output:
=== Compression Ratio Analysis ===
=== Token Estimate: source.md ===
...
=== Token Estimate: source.crux.mdc ===
...
=== Compression Summary ===
Source tokens: 397
CRUX tokens: 140
Ratio: 35.2% of original
Reduction: 64.8%
Target (≤20%): NO
--cksum <file>Get checksum of a file, formatted for CRUX frontmatter sourceChecksum field.
Output:
=== Checksum: example.md ===
Checksum: 1234567890
---
FRONTMATTER: "1234567890"
| Content Type | Chars/Token | Notes | |--------------|-------------|-------| | Prose (markdown) | 4.0 | English text, headers, lists | | Code blocks | 3.5 | More symbols, shorter identifiers | | Special chars | 1.0 | CRUX Unicode symbols |
CRUX delimiters and symbols that count as 1 token each:
« » ⟨ ⟩→ ← ≻ ≺⊤ ⊥ ∀ ∃ ¬ ∋⊳ ⊲≥ ≤ ≠Δ Ρ Λ Π Κ Γ Φ Ω⊛ ◊ θBoth modes produce identical output for identical input:
For compression tasks:
--cksum <source> → use FRONTMATTER value for sourceChecksum--token-count <source> → use for beforeTokens--token-count <crux> → use for afterTokens--token-count --ratio <source> <crux> → check Target (≤20%)documentation
Guide for managing X-Fidelity releases using the unified release system. Use when releasing, versioning, troubleshooting release issues, or writing commit messages.
documentation
Guide for executing engineering plans through coordinated subagent work. Use when executing existing plans from knowledge/plans/ directory.
development
Guide for updating X-Fidelity documentation including README and website. Use when updating docs, adding new features to documentation, or ensuring docs stay in sync with code.
tools
Guide for debugging X-Fidelity analysis issues. Use when troubleshooting analysis failures, rule evaluation problems, VSCode extension issues, or unexpected results.