akaszubski/consistency-enforcement
plugins/autonomous-dev/skills/archived/consistency-enforcement/SKILL.md
Documentation consistency enforcement - prevents drift between README.md and actual codebase state. Auto-activates when updating docs, committing changes, or working with skills/agents/commands.
$ install --global
skillsauthnpx skillsauth add akaszubski/autonomous-dev consistency-enforcementInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 3, 2026, 8:43 AM6.9s1 file scanned
SKILL.md
- name:
- consistency-enforcement
- version:
- 1.1.0
- type:
- knowledge
- description:
- Documentation consistency enforcement - prevents drift between README.md and actual codebase state. Auto-activates when updating docs, committing changes, or working with skills/agents/commands.
- keywords:
- readme, documentation, commit, sync, update, skill, agent, command, count, marketplace, consistency, drift
- auto_activate:
- false
- allowed-tools:
- [Read]
Consistency Enforcement Skill
Layer 4 Defense Against Documentation Drift
Auto-activates to maintain documentation consistency when working on docs, skills, agents, or commands.
See: workflow.md for step-by-step scenarios See: templates.md for checklists and commands
When This Activates
Keywords: "readme", "documentation", "docs", "commit", "sync", "update", "skill", "agent", "command", "count", "marketplace", "consistency", "drift"
Critical Consistency Rules
Rule 1: README.md is Source of Truth
All counts must match reality:
# Count actual resources
ls -d plugins/autonomous-dev/skills/*/ | wc -l # Skills
ls plugins/autonomous-dev/agents/*.md | wc -l # Agents
ls plugins/autonomous-dev/commands/*.md | wc -l # Commands
Rule 2: All Docs Must Match README.md
These files MUST show the same counts:
README.md(primary source)docs/SYNC-STATUS.mddocs/UPDATES.mdINSTALL_TEMPLATE.md.claude-plugin/marketplace.json(metrics)
Rule 3: Never Reference Non-Existent Skills
# Verify skill exists before referencing
ls -1 plugins/autonomous-dev/skills/
Rule 4: marketplace.json Matches Reality
{
"metrics": {
"agents": 8,
"skills": 12,
"commands": 21
}
}
4-Layer Defense System
| Layer | Location | Purpose |
|-------|----------|---------|
| 1 | tests/test_documentation_consistency.py | Automated CI/CD enforcement |
| 2 | agents/doc-master.md | Agent memory checklist |
| 3 | hooks/validate_docs_consistency.py | Pre-commit hook (optional) |
| 4 | This skill | Auto-reminder during work |
Run Tests
pytest tests/test_documentation_consistency.py -v
Quick Workflow
When adding/removing skills, agents, or commands:
- Update README.md count
- Update cross-reference files (SYNC-STATUS.md, UPDATES.md, etc.)
- Update marketplace.json metrics
- Run consistency tests
- Commit
See: workflow.md for detailed scenarios
Why This Matters
Documentation drift causes user confusion:
- README shows "9 Skills" but plugin has 12
- README mentions skill that doesn't exist
- User tries to use non-existent feature
With 4-layer defense:
- Layer 1: Tests fail in CI/CD
- Layer 2: doc-master catches before docs.json
- Layer 3: Pre-commit hook blocks commit
- Layer 4: This skill reminds during work
Result: Documentation always matches reality
Integration
Works with:
- documentation-guide: HOW to write docs
- git-workflow: HOW to commit changes
- project-management: PROJECT.md consistency
Related Files
- workflow.md - Step-by-step scenarios
- templates.md - Checklists and commands
Related Skills
akaszubski/content-allocation
development
VerifiedTrustedCommunity
One topic, one home. Routes content to its canonical store (CLAUDE.md, PROJECT.md, MEMORY.md, docs/, memory/) and audits for duplication. TRIGGER when: auditing CLAUDE.md/PROJECT.md/MEMORY.md sizes, deduplicating docs, applying the content-allocation pattern to a new repo, running /align --content. DO NOT TRIGGER when: implementing features, writing tests, routine code edits, debugging.
28SKILL.mdUpdated May 28, 2026
akaszubski/testing-guide
development
VerifiedTrustedCommunity
GenAI-first testing with structural assertions, congruence validation, and tier-based test structure. Use when writing tests, setting up test infrastructure, or validating coverage. TRIGGER when: test, pytest, coverage, TDD, test patterns, congruence, validation. DO NOT TRIGGER when: production code implementation, documentation, config-only changes.
28SKILL.mdUpdated Apr 3, 2026
akaszubski/prompt-engineering
testing
VerifiedTrustedCommunity
Prompt engineering patterns for writing agent prompts and skill files — constraint budgets, register shifting, HARD GATE patterns, anti-personas. Use when writing or reviewing agents/*.md or skills/*/SKILL.md. TRIGGER when: agent prompt, skill file, prompt engineering, model-tier compensation, HARD GATE, prompt quality. DO NOT TRIGGER when: user-facing docs, README, CHANGELOG, config files.
21SKILL.mdUpdated Apr 15, 2026
akaszubski/planning-workflow
testing
VerifiedTrustedCommunity
7-step planning workflow for pre-implementation design. Enforced by plan_gate hook, critiqued by plan-critic agent. Use when creating plans, design documents, or architecture decisions before implementation. TRIGGER when: plan, planning, /plan, design document, architecture decision. DO NOT TRIGGER when: implementation, coding, testing.
21SKILL.mdUpdated Apr 15, 2026