grazianoguiducci/version-check
plugins/d-nd-core/skills/version-check/SKILL.md
Check Claude Code version and identify new features relevant to the D-ND ecosystem. Use after Claude Code updates to discover what capabilities have changed.
$ install --global
skillsauthnpx skillsauth add grazianoguiducci/d-nd-seed version-checkInstall 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 22, 2026, 8:03 PM10.5s1 file scanned
SKILL.md
- name:
- version-check
- description:
- Check Claude Code version and identify new features relevant to the D-ND ecosystem. Use after Claude Code updates to discover what capabilities have changed.
Version Check — Claude Code Update Awareness
After a Claude Code update, run this to understand what changed and whether the D-ND plugin should adapt.
Check current version
The system_awareness hook reports Claude Code version at session start. If you see a version change, investigate.
What to check after an update
- New hook events: Does the new version support hook events we don't use yet?
- New tool capabilities: Are there new tools available?
- Plugin system changes: Has the plugin format evolved?
- Performance improvements: Memory fixes, context window changes?
- Security changes: New permission modes, sandbox changes?
Investigation procedure
# Check changelog
# Search web for: "Claude Code [version] changelog"
# Or check: https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md
Feature mapping (what matters for D-ND)
| Claude Code Feature | D-ND Relevance | Current status | |--------------------|--------------------|----------------| | HTTP hooks | Could replace shell hooks for node messaging | Not yet used | | Agent worktree isolation | Experimental branches per node | Available | | Fast mode 1M context | Full context in fast mode | Available | | Background agents | Async work across nodes | Available | | Plugin marketplace | Public seed distribution | Ready to use | | Auto-memory | Supplements our MEMORY.md system | Active | | /simplify command | Post-session code review | Available | | MCP servers | External tool connections | Available |
After assessment
- If new features are useful: update the plugin (bump version in plugin.json)
- If hooks need updating: modify hooks.json and scripts
- If new skills are needed: add to skills/
- Notify operator with findings and recommendations
$ARGUMENTS
Eval
Trigger Tests
Appropriate prompts for this skill -> activates
Unrelated prompts -> does NOT activate
Fidelity Tests
Given valid input: produces expected output
Given edge case: handles gracefully
Always reports what was done
Related Skills
grazianoguiducci/third-act
testing
VerifiedTrustedCommunity
Closure reflection protocol. After a significant work block concludes (feature shipped, session ending, major commit landed, cross-node coordination resolved), runs a 10-question interview that extracts meaning, impact, and next questions — then emits multiple audience-specific artifacts (changelog, external editorial, AI integration docs, memory crystal, backlog seed). Turns implicit maturation into explicit narrative. Use at the end of meaningful work, not after trivial edits.
1SKILL.mdUpdated May 2, 2026
grazianoguiducci/sieve-orchestrator
testing
VerifiedTrustedCommunity
The neutral form of the D-ND method. Meta-skill that recognizes context and orients toward the right specialization (cec, autologica, cascade, assertion-verifier, etc.). Activate at the start of a non-trivial work block or when input matches trigger words ('where are we', 'what here', 'orchestrate', 'connect', 'sieve this').
1SKILL.mdUpdated May 2, 2026
grazianoguiducci/publish-safe
development
VerifiedTrustedCommunity
Five mechanical gates for any content publish pipeline with CMS + rendering layers. Prevents false security: 'API returned 200' does not mean 'visitor sees clean content'. Use when writing content to a multi-layer serving system (CMS API, static files, prerendered HTML, cached copies).
1SKILL.mdUpdated May 2, 2026
grazianoguiducci/poly-consult
testing
VerifiedTrustedCommunity
Multi-node consultation protocol for high-leverage decisions. Dispatches the same question to N independent LLM/agent nodes in isolation, then synthesizes their responses into a summa that exposes convergence (high-confidence claims), dissensus (real uncertainty zones), and emergent points (insights no single node produced). Reduces single-node training bias. Supports recursive escalation for stable-state convergence. Use for decisions that propagate via A14 cascade — seed updates, crystallizations, advisory→mechanical promotions, high-visibility copy, lab result interpretation.
1SKILL.mdUpdated May 2, 2026