菜单
Agent fleet health utilities — path preflight checker and auto-remediating weekly doctor with apply mode.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Local-only multi-agent orchestrator with token optimization, 6-signal composite routing, and persistent memory. Routes all tasks through local executor bridges (Claude Code, Hermes, Gemini, Codex) with DAG dependencies, auto-episode creation, and cognitive profiles.
Zouroboros self-healing watchdog that monitors scheduled agent models and automatically switches failing agents to backup models, restoring originals when they recover.
Hybrid SQLite + Vector persona memory system for Zo Computer. Episodic memory with temporal queries, graph-boosted search, BFS path finding, knowledge gap analysis, auto-capture pipeline, and per-workload model routing. Default generation workloads use OpenAI `gpt-4o-mini`; embeddings use OpenAI `text-embedding-3-small`.
Security governance gate for AI agent skills, backed by NVIDIA SkillSpector. Statically scans a skill (local path, directory, zip, or Git URL) for 65 vulnerability patterns across 16 categories (prompt injection, data exfiltration, privilege escalation, supply chain, excessive agency, tool/MCP misuse, dangerous code via AST, YARA signatures) and returns a 0-100 risk score with a SAFE / REVIEW / DO_NOT_INSTALL recommendation. Use BEFORE adopting any third-party skill, and for the periodic baseline scan of the Skills/ directory.
Detector for model classifier SOFT-blocks — refusals, filtered-to-empty, truncated-with-disclaimer, content-policy flags — that masquerade as successful empty output to existing infrastructure (agent-model-healer only catches HARD failures: HTTP 4xx/5xx, timeouts, genuine empties). Classifies an output as soft_block / genuine_empty / ok using a per-provider signal catalog, then routes a per-domain fallback (security → broader-tolerance model, bio/chem → human review, distillation → refuse-by-design, never routed around). Every block + fallback is appended to an audit ledger. A quarterly system-card-diff agent flags expanded classifier scope so the catalog stays current.
Rendered-output verification station for the swarm post-flight eval. After a maker subagent produces a visual deliverable (UI/route/site), the station captures a full-page screenshot via agent-browser, then an independent verifier model (not equal to author, per aiewf P0-2) reads the screenshot against seed acceptance criteria + project DESIGN.md tokens + prior screenshots. Match marks the task complete; mismatch emits a structured visual diff for the maker's next iteration. The verifier is the exit condition, not the maker. Recurring visual failure modes graduate to instincts.yaml via the extract-patterns gate (ZOU-452).
| name | agent-doctor |
| description | Agent fleet health utilities — path preflight checker and auto-remediating weekly doctor with apply mode. |
| compatibility | Created for Zo Computer |
| metadata | {"author":"marlandoj.zo.computer"} |
Auto-remediating fleet doctor. Audits all scheduled agents for cost waste, zombies, duplicates, and hygiene drift.
bun Skills/agent-doctor/scripts/doctor.ts # report-only (diagnose)
bun Skills/agent-doctor/scripts/doctor.ts apply # auto-apply safe fixes
bun Skills/agent-doctor/scripts/doctor.ts summary # one-line summary
bun Skills/agent-doctor/scripts/doctor.ts zombies # single check
Exit codes: 0 = clean, 2 = findings present (or changes applied), 1 = apply error.
Auto-applied (safe): zombie deactivation (no next_run), cost-fitness model downgrade, delivery-method silence. Manual review only: duplicates, instruction-hygiene, frequency-waste, persona-fitness, schedule-collision, instruction-length, output-delta.
Safety excludes (never mutated): 01a6df7e-6bd4-4772-bfe4-d04404106b8b (Agent Doctor self), 14cfe6a6-105e-4160-bf95-a93e95f871a0 (Model Healer).
Requires assets/model-tiers.json in the same skill directory.
Verifies that all given file paths exist on disk. Exits 0 if all OK, exits 1 with BROKEN PATH: <path> lines for any missing files.
bun Skills/agent-doctor/scripts/preflight-paths.ts /path/to/file1.ts /path/to/file2.ts