Followup audit of the single-source-of-truth agent-docs rollout. Several AI.dev prompts and skills still taught agents the old 8-file pattern (which would re-introduce drift) and the generator script emitted a misleading summary in --no-commit mode. AI.dev guides: - Delete AI.dev/SKILLS/update-agent-docs.md — entire doc taught the old 8-file pattern. Canonical reference is now .windsurf/workflows/repo_update-agent-docs.md. - AI.dev/SKILLS/index.md + README.md: replace dangling 'Update Agent Documentation' link with pointers to agent-behavior-guidelines.md, agent-onboarding.md, and the workflow doc. - AI.dev/SKILLS/scan-repo-context.md: remove instructions to read .windsurfrules / write .cursorrules. Point at the canonical behavior file. - AI.dev/PROMPTS/new-product-scaffold.md: remove .windsurfrules and CLAUDE.md from the scaffold tree. Add deprecated-files callout + regeneration hint. - AI.dev/PROMPTS/agents-md-sync.md: drop 'Step 4 update CLAUDE.md', point at the generator instead. Remove CLAUDE.md from `git add`. - AI.dev/PROMPTS/ecosystem-audit.md: replace 'CLAUDE.md exists?' with 'canonical-behavior-pointer block present? legacy files absent?'. Script UX: - scripts/update-agent-docs.sh: stop printing 'All repos already in sync' when --no-commit suppressed commits or --dry-run was used. Emit accurate per-mode summaries instead.
4.3 KiB
4.3 KiB
| name | description | argument-hint | agent |
|---|---|---|---|
| ecosystem-audit | Run a full health audit across the ByteLyst ecosystem — builds, tests, types, dependencies, config drift, and produce an actionable dashboard. | Depth and focus, e.g. "full audit", "quick health check", "backend focus", "config drift only" | agent |
Ecosystem Audit Prompt
Produce a comprehensive health dashboard across all ByteLyst repos with actionable findings.
Context — ByteLyst Ecosystem
37 repos in D:\BYTELYST\CODE\, including:
Core platform:
learning_ai_common_plat— shared packages + services
Active products (with backends):
learning_ai_efforise(EffoRise, port 4020)learning_ai_flowmonk(FlowMonk, port 4017)learning_ai_dev_intelli(DevIntelli, port 4021)learning_ai_peakpulse(PeakPulse, port 4010)learning_ai_clock(ChronoMind, port 4011)learning_ai_jarvis_jr(JarvisJr, port 4012)learning_ai_fastgap(NomGap, port 4013)learning_multimodal_memory_agents(MindLyst, port 4014)
Active products (platform-only):
learning_ai_auth_app(ByteLyst Auth — no backend)learning_ai_notes(NoteLett)learning_ai_trails(ActionTrail)
Tooling & infrastructure:
learning_ai_local_llms,learning_ai_local_memory_gptlearning_windsurf_setup,learning_claude_code_setup,learning_sidecar_setuplearning_agent_monitoring_fx,learning_agentic_tools_portal
Audit Dimensions
1. Build Health
For each repo with a package.json:
pnpm install --frozen-lockfile # Can deps resolve?
pnpm build # Does it compile?
2. Type Safety
pnpm typecheck # TypeScript clean?
3. Test Health
pnpm test --run # All tests pass?
Record: total tests, passing, failing, skipped.
4. Config Consistency
Check alignment across repos:
.npmrcmatches canonical template?.nvmrcspecifies Node 22?tsconfig.jsonextends base correctly?.editorconfigpresent?shared/product.jsoncorrect?.env.exampleup to date?
5. Package Version Alignment
Verify shared deps are on compatible versions:
- TypeScript, Zod, Fastify, Vitest, React, Next.js
@bytelyst/*packages (all onworkspace:*orfile:)
6. Security
pnpm audit
# Check for high/critical vulnerabilities
7. Documentation Currency
- AGENTS.md exists and matches current layout?
- AGENTS.md contains the canonical-behavior-pointer block? (
bash scripts/check-agent-docs-drift.sh) - README.md has setup instructions?
- Legacy agent files removed? (
.cursorrules,.windsurfrules,.clinerules,CLAUDE.md— replaced by single-source-of-truth pattern)
8. Git Hygiene
- Any repos with uncommitted changes?
- Any repos behind remote?
- Any repos with merge conflicts?
Output: Ecosystem Dashboard
# ByteLyst Ecosystem Health Dashboard
> Generated: <date>
## Executive Summary
- Repos audited: N
- 🟢 Healthy: N
- 🟡 Issues: N
- 🔴 Critical: N
## Scorecard
| Repo | Build | Types | Tests | Config | Deps | Security | Docs | Git |
|------|-------|-------|-------|--------|------|----------|------|-----|
| common_plat | ✅ | ✅ | 876/876 | ✅ | ✅ | ✅ | ✅ | clean |
| efforise | ✅ | ✅ | 65/65 | ✅ | ✅ | ⚠️ 2 | ✅ | clean |
| flowmonk | ✅ | ⚠️ 3 | 196/196 | ✅ | ✅ | ✅ | ✅ | dirty |
| ... | | | | | | | | |
## Critical Issues (Fix First)
| Repo | Issue | Impact | Fix |
|------|-------|--------|-----|
## Action Queue (Prioritized)
| # | Repo | Action | Effort | Impact |
|---|------|--------|--------|--------|
| 1 | ... | ... | S/M/L | High/Med/Low |
## Config Drift Report
| Config | Expected | Drifted Repos |
|--------|----------|--------------|
| .npmrc | canonical template | <list> |
| .nvmrc | "22" | <list> |
## Dependency Alignment
| Package | Version | Aligned | Misaligned |
|---------|---------|---------|-----------|
Execution Tips
- Start with common_plat — it's the foundation
- Skip node_modules-only repos — focus on active development repos
- Parallelize where possible — run independent repo checks simultaneously
- Time-box expensive checks — if
pnpm installtakes >2min, skip and note
Commit
# If you fix issues during audit:
cd <repo>
git add .
git commit -m "fix(<scope>): resolve audit findings
- <finding 1>
- <finding 2>"
git push