brdohman/platform-awareness
.claude/skills/platform-awareness/SKILL.md
Track Claude Code platform updates, model changes, and new features. Manages cached documentation snapshots and produces change reports.
$ install --global
skillsauthnpx skillsauth add brdohman/agile-maestro platform-awarenessInstall 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 24, 2026, 8:57 PM1.9s1 file scanned
SKILL.md
- name:
- platform-awareness
- description:
- Track Claude Code platform updates, model changes, and new features. Manages cached documentation snapshots and produces change reports.
- disable-model-invocation:
- true
- user-invocable:
- false
Platform Awareness Skill
Purpose
Self-contained system for tracking Claude Code platform changes with zero external dependencies. Fetches public documentation, diffs against cached snapshots, and reports what changed — so the toolkit can stay current with new models, features, and deprecations.
Commands
| Command | When to Use | Time |
|---------|-------------|------|
| /check-updates | Quick scan for new releases or model changes | ~30 sec |
| /deep-dive-updates | Full analysis of all tracked sources | Monthly or after significant releases |
| /evolve | Self-audit: compare platform capabilities against toolkit usage | When planning improvements |
Key Files
| File | Purpose |
|------|---------|
| references/feature-reference.md | What we know Claude Code can do |
| references/model-reference.md | Known models, context windows, deprecations |
| references/last-checked.json | Timestamps, tracked docs, tracked sources for change detection |
| references/external-sources.md | Where to look beyond official docs (blog, X, Piebald-AI, etc.) |
| references/discoveries.md | What we've found — organized by topic with source URLs |
| references/watchlist.md | Items to actively check next deep dive |
| snapshots/ | Cached doc pages used for diffing |
| update-log.md | Audit trail of detected changes and user approvals |
Data Sources
Official (authoritative)
https://code.claude.com/docs/llms.txt— canonical index of Claude Code docshttps://raw.githubusercontent.com/anthropics/claude-code/main/CHANGELOG.md— release changeloghttps://platform.claude.com/docs/en/release-notes/overview— model/API release noteshttps://www.anthropic.com/news— Anthropic blog (major launches)
Community (verify before adopting)
https://x.com/bcherny— Claude Code creator, previews + confirmationshttps://x.com/AnthropicAI— Official Anthropic X accounthttps://github.com/Piebald-AI/claude-code-system-prompts— Reverse-engineered system prompts (catches undocumented features)https://releasebot.io/updates/anthropic/claude-code— Release aggregator
See references/external-sources.md for full source catalog with verification protocol.
How It Works
- Fetch — Pull current versions of tracked sources
- Diff — Compare against cached snapshots in
snapshots/ - Categorize — Tag changes: new model, deprecation, feature, breaking change
- Report — Present a human-readable summary of what changed
- Approve — User reviews and confirms the report is accurate
- Update — Snapshots and reference files updated, entry added to
update-log.md
No changes are written until the user approves. The skill never auto-modifies toolkit files.
When to Run
/check-updates— Anytime before starting a new epic or when model selection questions arise/deep-dive-updates— Monthly cadence, or immediately after an Anthropic release announcement/evolve— When planning toolkit improvements or after a major platform shift
Related Skills
brdohman/xctest-patterns
testing
VerifiedTrustedCommunity
XCTest patterns for macOS Swift apps. Unit tests, async tests, Core Data tests, mock patterns, and assertion reference. Use when writing or reviewing tests.
2SKILL.mdUpdated Apr 16, 2026
brdohman/workflow-state
tools
VerifiedTrustedCommunity
How to transition workflow state between review stages. Rules for setting review_stage and review_result fields on Stories and Epics.
2SKILL.mdUpdated Apr 16, 2026
brdohman/workflow-comments
documentation
VerifiedTrustedCommunity
Comment structure and rules for task workflow updates. Use when adding any comment to a task during implementation, review, or fix cycles.
2SKILL.mdUpdated Apr 16, 2026
brdohman/validate-task
testing
VerifiedTrustedCommunity
Validate task/story/epic/bug/techdebt metadata against schema v2.0. Run after TaskCreate or TaskUpdate to verify compliance. Returns pass/fail with actionable details.
2SKILL.mdUpdated Apr 16, 2026