Menu
Safe OpenClaw gateway configuration changes with validation and auto-rollback
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Automated research subagent. Accepts a natural-language query, gathers sources from the knowledge graph (KG + BM25 + E5 + Web + Notion), performs SGR synthesis, generates validated knowledge cards, and writes them to the graph. Explicit trigger: "autosearch" — activates the subagent without confirmation. Soft triggers (require confirmation): "research", "analyze", "compare", "deep dive", "review".
SGR-guided knowledge graph node creation with canonical schema validation. Use when creating new nodes, updating existing nodes, or auditing graph health. Enforces closed vocabularies for node types, clusters, and relation types to prevent taxonomy drift. Triggers on: "create node", "add to graph", "new insight", "graph audit", "validate graph", "taxonomy check".
SGR-enhanced pool of cheap specialized subagents based on sgr-agent-core. Uses Schema-Guided Reasoning to boost mini/Flash models to near-Sonnet quality. Trigger: "sgr", "sgr pool", "cheap agent", "mini agent", "sgr-researcher", "sgr-verifier", "sgr-summarizer".
Design-before-code protocol. Routes new features, refactors, and complex changes through the appropriate design artifact BEFORE implementation begins. Use when the user asks to design a feature, write an RFC, think through architecture, plan a new skill, structure a large refactor, or define the implementation approach before coding. Triggers: "design", "RFC", "architecture", "new skill", "new feature", "large change", "need a plan", "design-architect", "tech spec", "ADR".
Subagent for generating PPTX presentations via Claude Code CLI + official pptx skill. Trigger: "presentation", "slides", "deck".
Multi-subagent framework. Allows the main agent to spawn specialized Claude Code subagents with specific skills. Each subagent runs autonomously (full agentic loop) and returns a structured result. Engine: Claude Code CLI (claude --bare -p). Trigger: "subagent", "spawn agent".
| name | config-guardian |
| description | Safe OpenClaw gateway configuration changes with validation and auto-rollback |
| version | 1.0.0 |
| author | Agent |
MANDATORY: Never edit /data/.openclaw/openclaw.json directly.
Any configuration change MUST go through Config Guardian.
The gateway performs a hot-reload on file change. An invalid config = gateway crash. Config Guardian validates changes BEFORE writing, creates a backup, and automatically rolls back if the gateway degrades after the change.
Execute via exec tool:
bash /data/.openclaw/workspace/scripts/config_guardian.sh set <key> <value>
Examples:
bash /data/.openclaw/workspace/scripts/config_guardian.sh set agents.defaults.heartbeat.every "2h"
bash /data/.openclaw/workspace/scripts/config_guardian.sh set agents.defaults.model.primary "anthropic/claude-sonnet-4-6"
bash /data/.openclaw/workspace/scripts/config_guardian.sh unset <key>
bash /data/.openclaw/workspace/scripts/config_guardian.sh patch '<json>'
Example:
bash /data/.openclaw/workspace/scripts/config_guardian.sh patch '{"agents":{"defaults":{"model":{"primary":"anthropic/claude-sonnet-4-6"}}}}'
bash /data/.openclaw/workspace/scripts/config_guardian.sh validate <file>
| Code | Meaning | Action |
|---|---|---|
| 0 | Successfully applied | None |
| 1 | Validation failed | Fix input data and retry |
| 2 | Applied but rolled back | Investigate docker logs --since 1m |
| 3 | Usage error | Check command syntax |
docker logs --since 1m <your-container-name>) and report the rollback reason.openclaw plugins enable/disable as a "fix" — it overwrites the config.edit or write to /data/.openclaw/openclaw.jsonopenclaw config set/unset directly (without the guardian wrapper)openclaw plugins enable/disable (overwrites config unpredictably)Безпечна зміна конфігурації OpenClaw gateway з валідацією та авто-відкатом. Ніколи не редагуйте openclaw.json напряму — всі зміни проходять через Config Guardian, який валідує, бекапить і автоматично відкочує при деградації.