mcpField
V
validate-counts

validate-counts

github.com/yonatangrossTesting & quality299119 installsUpdated today
Repository

About validate-counts

validate-counts checks whether hook, skill, and agent counts agree across OrchestKit’s authoritative sources. It compares filesystem counts with documentation and manifests, then reports discrepancies with file and field references.

Key features

  1. 01Count hooks, skills, and agents
  2. 02Compare authoritative sources
  3. 03Flag mismatches with file references
  4. 04Run full validation or raw counts

Use cases

  1. 01Checking count consistency before release
  2. 02Locating drift between manifests and documentation

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/yonatangross/orchestkit --skill validate-counts

After installing, type/validate-countsin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

test-cases.json
references/
count-locations.md
rules/
_sections.md
_template.md
drift-reporting.md
sources-authoritative.md
scripts/
count-all.sh
validate-counts.sh

Details

From the project README

Validate Counts

Checks that hook, skill, and agent counts are consistent across all authoritative sources in OrchestKit. Outputs a comparison table and flags drift with precise file references.

Quick Start

# Full validation: counts src/ vs CLAUDE.md and manifests (run from repo root)
bash src/skills/validate-counts/scripts/validate-counts.sh

# Just get raw counts from src/
bash src/skills/validate-counts/scripts/count-all.sh

Rules

CategoryRuleImpactKey Pattern
Count Sourcesrules/sources-authoritative.md (load ${CLAUDE_SKILL_DIR}/rules/sources-authoritative.md)HIGHFilesystem is authoritative; derived sources must match
Drift Detectionrules/drift-reporting.md (load ${CLAUDE_SKILL_DIR}/rules/drift-reporting.md)HIGHComparison table + flag with file:field references

Total: 2 rules across 2 categories

Workflow

  1. Run scripts/validate-counts.sh for full validation (counts + drift comparison), or scripts/count-all.sh for raw counts only
  2. Read CLAUDE.md — extract counts from Project Overview and Version section
  3. Read manifests/ork.json — check skill/agent/hook array lengths
  4. Build the comparison table (see rules/drift-reporting.md for format)
  5. Flag any mismatches with file + field references; otherwise output "All counts consistent."

References

Load on demand with Read("${CLAUDE_SKILL_DIR}/references/<file>"):

FileContent
count-locations.mdWhere every count lives and why drift happens

Related Skills

  • release-checklist — Uses validate-counts as step 5 of the release gate
  • doctor — Broader health check that includes count validation
  • audit-skills — Quality audit for skill structure and completeness

Common Mistakes

  1. Counting from plugins/ instead of src/ — plugins/ may be empty after an interrupted build
  2. Comparing against deleted alias manifests — only manifests/ork.json exists in v7
  3. Forgetting the hook breakdown: global + agent-scoped + skill-scoped must sum to total

Comments

Markdown supported