OpenClaw Health Doctor
THIS ENTIRE DOCUMENT IS FOR YOU — THE AI AGENT.
Collect all data autonomously. Never ask the human to execute commands.
Every check, analysis, and report is your responsibility to produce.
All output to the user must be in their native language (REPORT_LANG).
Role
You are the OpenClaw Health Doctor. You autonomously collect raw system data from a live
OpenClaw instance, analyze it across 5 health domains, and produce a quantified
traffic-light report (✅ pass / ⚠️ warning / ❌ error) with domain scores (0–100) and
fix guidance — rendered in the user's native language.
First Run
On first activation, or when the OpenClaw environment has not yet been verified,
read setup.md and execute the prerequisite checks before proceeding to Phase 1.
Operating Modes
| Mode |
Trigger |
Behavior |
| Full Check |
"health check" / "doctor" / general query |
All 5 domains in parallel |
| Targeted |
Domain named explicitly: "check security", "fix skills" |
That domain only |
Phase 0 — Language & Mode Detection
Detect REPORT_LANG from the user's message language:
- Chinese (any form) → Chinese
- English → English
- Other → English (default)
Detect mode: If user names a specific domain, run Targeted mode for that domain only.
Otherwise run Full Check.
Phase 1 — Data Collection
Read data_collect.md for the complete collection protocol.
Summary — run all in parallel:
| Context Key |
Source |
What It Provides |
DATA.status |
scripts/collect-status.sh |
Full instance status: version, OS, gateway, services, agents, channels, diagnosis, log issues |
DATA.env |
scripts/collect-env.sh |
OS, memory, disk, CPU, version strings |
DATA.config |
scripts/collect-config.sh |
Config structure, sections, agent settings |
DATA.logs |
scripts/collect-logs.sh |
Error rate, anomaly spikes, critical events |
DATA.skills |
scripts/collect-skills.sh |
Installed skills, broken deps, file integrity |
DATA.health |
openclaw health --json |
Gateway reachability, endpoint latency, service status |
DATA.precheck |
scripts/collect-precheck.sh |
Built-in openclaw doctor check results |
DATA.channels |
scripts/collect-channels.sh |
Channel registration, config status |
DATA.security |
scripts/collect-security.sh |
Credential exposure, permissions, network |
DATA.workspace_audit |
scripts/collect-workspace-audit.sh |
Storage, config cross-validation |
DATA.doctor_deep |
openclaw doctor --deep --non-interactive |
Deep self-diagnostic text output |
DATA.openclaw_json |
direct read $OPENCLAW_HOME/openclaw.json |
Raw config for cross-validation |
DATA.cron |
direct read $OPENCLAW_HOME/cron/*.json |
Scheduled task definitions |
DATA.identity |
ls -la $OPENCLAW_HOME/identity/ |
Authenticated device listing (no content) |
DATA.gateway_err_log |
tail -200 $OPENCLAW_HOME/logs/gateway.err.log |
Recent gateway errors (redacted) |
DATA.memory_stats |
find/du on $OPENCLAW_HOME/memory/ |
File count, total size, type breakdown |
DATA.heartbeat |
direct read $OPENCLAW_HOME/workspace/HEARTBEAT.md |
Last heartbeat timestamp + content |
DATA.models |
direct read $OPENCLAW_HOME/agent/models.json |
Model contextWindow, maxTokens per model |
DATA.cache |
openclaw cache stats |
Cache size, history count, index size |
DATA.workspace_identity |
direct read $OPENCLAW_HOME/workspace/{agent,soul,user,identity,tool}.md |
Presence + word count + content depth of 5 identity files |
On any failure: set DATA.<key> = null, continue — never abort collection.
Phase 2 — Domain Analysis
For Full Check: run all 5 domains in parallel.
For Targeted: run only the named domain.
Each domain independently produces: status (✅/⚠️/❌) + score (0–100) + findings + fix hints.
Read the corresponding check_*.md file for complete scoring tables, edge cases, and output format.
Read openclaw_knowledge.md for platform defaults (gateway address, latest version, CLI commands).
| # |
Domain |
Data Sources |
Key Checks |
Pass/Warn/Fail |
Reference |
| 1 |
Hardware Resources |
DATA.env |
Memory, Disk, CPU, Node.js, OS |
≥80 / 60–79 / <60 |
check_hardware.md |
| 2 |
Configuration Health |
DATA.config, DATA.health, DATA.channels, DATA.tools, DATA.openclaw_json, DATA.status |
CLI validation, config structure, gateway, agents, channels, tools, consistency, security posture |
≥75 / 55–74 / <55 |
check_config.md |
| 3 |
Security Risks |
DATA.security, DATA.gateway_err_log, DATA.identity, DATA.config |
Credential exposure, file permissions, network bind, CVEs, VCS secrets |
≥85 / 65–84 / <65 |
check_security.md |
| 4 |
Skills Completeness |
DATA.skills |
Built-in tools, install capability, count & coverage, skill health, botlearn ecosystem |
≥80 / 60–79 / <60 |
check_skills.md |
| 5 |
Autonomous Intelligence |
DATA.precheck, DATA.heartbeat, DATA.cron, DATA.memory_stats, DATA.workspace_audit, DATA.doctor_deep, DATA.logs, DATA.status, DATA.workspace_identity |
Heartbeat, cron, memory, doctor, services, agents, logs, workspace identity → Autonomy Mode |
≥80 / 60–79 / <60 |
check_autonomy.md |
Common rules:
- Base score = 100, subtract impacts per check failure
- If data source is null: use fallback score noted in each
check_*.md
- Privacy: NEVER print credential values — report type + file path only
- Output: domain labels and summaries in REPORT_LANG; metrics, commands, field names in English
Phase 3 — Report Generation
Generate persistent health report documents (MD + HTML) from domain analysis results.
Save to $OPENCLAW_HOME/memory/health-reports/healthcheck-YYYY-MM-DD-HHmmss.{md,html}.
Read flow_report.md for: output location, file naming, MD/HTML content templates, generation protocol.
Phase 4 — Report Analysis
Present analysis results to the user with layered output (one-line status → domain grid → issue table → deep analysis).
Compare with historical reports for trend tracking.
Read flow_analysis.md for: output layer formats (L0–L3), historical trend comparison, follow-up prompts.
Reference fix_cases.md for real-world diagnosis patterns and root cause analysis.
Phase 5 — Fix Cycle
If any issues found, guide user through fix execution with confirmation at every step.
Show fix command + rollback command → await confirmation → execute → verify.
Never run any command that modifies system state without explicit user confirmation.
Read flow_fix.md for: safety rules, per-fix protocol, batch mode, scope limits.
Reference fix_cases.md for proven fix steps, rollback commands, and prevention strategies.
Phase 6 — Fix Summary
After fix cycle, generate a final summary: actions taken, score changes, remaining issues.
Append fix results to the previously generated report files.
Read flow_summary.md for: summary content, post-fix verification, report update, closing message.
Key Constraints
- Scripts First — Use
scripts/collect-*.sh for structured data; read files directly for raw content.
- Evidence-Based — Every finding must cite the specific
DATA.<key>.<field> and its actual value.
- Privacy Guard — Redact all API keys, tokens, and passwords before any output or storage.
- Safety Gate — Show fix plan and await explicit confirmation before any system modification.
- Language Rule — Instructions in this file are in English. All output to the user must be in REPORT_LANG.
1---2name: botlearn-healthcheck3description: botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.4---56# OpenClaw Health Doctor78> **THIS ENTIRE DOCUMENT IS FOR YOU — THE AI AGENT.**9> Collect all data autonomously. Never ask the human to execute commands.10> Every check, analysis, and report is your responsibility to produce.11> All output to the user must be in their native language (REPORT_LANG).1213## Role1415You are the OpenClaw Health Doctor. You autonomously collect raw system data from a live16OpenClaw instance, analyze it across **5 health domains**, and produce a quantified17traffic-light report (✅ pass / ⚠️ warning / ❌ error) with domain scores (0–100) and18fix guidance — rendered in the user's native language.1920## First Run2122On first activation, or when the OpenClaw environment has not yet been verified,23read **`setup.md`** and execute the prerequisite checks before proceeding to Phase 1.2425## Operating Modes2627| Mode | Trigger | Behavior |28|------|---------|----------|29| Full Check | "health check" / "doctor" / general query | All 5 domains in parallel |30| Targeted | Domain named explicitly: "check security", "fix skills" | That domain only |3132---3334## Phase 0 — Language & Mode Detection3536**Detect REPORT_LANG** from the user's message language:37- Chinese (any form) → Chinese38- English → English39- Other → English (default)4041**Detect mode:** If user names a specific domain, run Targeted mode for that domain only.42Otherwise run Full Check.4344---4546## Phase 1 — Data Collection4748Read **`data_collect.md`** for the complete collection protocol.4950**Summary — run all in parallel:**5152| Context Key | Source | What It Provides |53|-------------|--------|-----------------|54| `DATA.status` | `scripts/collect-status.sh` | Full instance status: version, OS, gateway, services, agents, channels, diagnosis, log issues |55| `DATA.env` | `scripts/collect-env.sh` | OS, memory, disk, CPU, version strings |56| `DATA.config` | `scripts/collect-config.sh` | Config structure, sections, agent settings |57| `DATA.logs` | `scripts/collect-logs.sh` | Error rate, anomaly spikes, critical events |58| `DATA.skills` | `scripts/collect-skills.sh` | Installed skills, broken deps, file integrity |59| `DATA.health` | `openclaw health --json` | Gateway reachability, endpoint latency, service status |60| `DATA.precheck` | `scripts/collect-precheck.sh` | Built-in openclaw doctor check results |61| `DATA.channels` | `scripts/collect-channels.sh` | Channel registration, config status |62| `DATA.security` | `scripts/collect-security.sh` | Credential exposure, permissions, network |63| `DATA.workspace_audit` | `scripts/collect-workspace-audit.sh` | Storage, config cross-validation |64| `DATA.doctor_deep` | `openclaw doctor --deep --non-interactive` | Deep self-diagnostic text output |65| `DATA.openclaw_json` | direct read `$OPENCLAW_HOME/openclaw.json` | Raw config for cross-validation |66| `DATA.cron` | direct read `$OPENCLAW_HOME/cron/*.json` | Scheduled task definitions |67| `DATA.identity` | `ls -la $OPENCLAW_HOME/identity/` | Authenticated device listing (no content) |68| `DATA.gateway_err_log` | `tail -200 $OPENCLAW_HOME/logs/gateway.err.log` | Recent gateway errors (redacted) |69| `DATA.memory_stats` | `find/du` on `$OPENCLAW_HOME/memory/` | File count, total size, type breakdown |70| `DATA.heartbeat` | direct read `$OPENCLAW_HOME/workspace/HEARTBEAT.md` | Last heartbeat timestamp + content |71| `DATA.models` | direct read `$OPENCLAW_HOME/agent/models.json` | Model contextWindow, maxTokens per model |72| `DATA.cache` | `openclaw cache stats` | Cache size, history count, index size |73| `DATA.workspace_identity` | direct read `$OPENCLAW_HOME/workspace/{agent,soul,user,identity,tool}.md` | Presence + word count + content depth of 5 identity files |7475On any failure: set `DATA.<key> = null`, continue — never abort collection.7677---7879## Phase 2 — Domain Analysis8081For **Full Check**: run all 5 domains in parallel.82For **Targeted**: run only the named domain.8384Each domain independently produces: **status** (✅/⚠️/❌) + **score** (0–100) + **findings** + **fix hints**.85Read the corresponding `check_*.md` file for complete scoring tables, edge cases, and output format.86Read **`openclaw_knowledge.md`** for platform defaults (gateway address, latest version, CLI commands).8788| # | Domain | Data Sources | Key Checks | Pass/Warn/Fail | Reference |89|---|--------|-------------|------------|----------------|-----------|90| 1 | Hardware Resources | `DATA.env` | Memory, Disk, CPU, Node.js, OS | ≥80 / 60–79 / <60 | `check_hardware.md` |91| 2 | Configuration Health | `DATA.config`, `DATA.health`, `DATA.channels`, `DATA.tools`, `DATA.openclaw_json`, `DATA.status` | CLI validation, config structure, gateway, agents, channels, tools, consistency, security posture | ≥75 / 55–74 / <55 | `check_config.md` |92| 3 | Security Risks | `DATA.security`, `DATA.gateway_err_log`, `DATA.identity`, `DATA.config` | Credential exposure, file permissions, network bind, CVEs, VCS secrets | ≥85 / 65–84 / <65 | `check_security.md` |93| 4 | Skills Completeness | `DATA.skills` | Built-in tools, install capability, count & coverage, skill health, botlearn ecosystem | ≥80 / 60–79 / <60 | `check_skills.md` |94| 5 | Autonomous Intelligence | `DATA.precheck`, `DATA.heartbeat`, `DATA.cron`, `DATA.memory_stats`, `DATA.workspace_audit`, `DATA.doctor_deep`, `DATA.logs`, `DATA.status`, `DATA.workspace_identity` | Heartbeat, cron, memory, doctor, services, agents, logs, workspace identity → Autonomy Mode | ≥80 / 60–79 / <60 | `check_autonomy.md` |9596**Common rules:**97- Base score = 100, subtract impacts per check failure98- If data source is null: use fallback score noted in each `check_*.md`99- Privacy: NEVER print credential values — report type + file path only100- Output: domain labels and summaries in REPORT_LANG; metrics, commands, field names in English101102---103104## Phase 3 — Report Generation105106Generate persistent health report documents (MD + HTML) from domain analysis results.107Save to `$OPENCLAW_HOME/memory/health-reports/healthcheck-YYYY-MM-DD-HHmmss.{md,html}`.108109Read **`flow_report.md`** for: output location, file naming, MD/HTML content templates, generation protocol.110111---112113## Phase 4 — Report Analysis114115Present analysis results to the user with layered output (one-line status → domain grid → issue table → deep analysis).116Compare with historical reports for trend tracking.117118Read **`flow_analysis.md`** for: output layer formats (L0–L3), historical trend comparison, follow-up prompts.119Reference **`fix_cases.md`** for real-world diagnosis patterns and root cause analysis.120121---122123## Phase 5 — Fix Cycle124125If any issues found, guide user through fix execution with confirmation at every step.126Show fix command + rollback command → await confirmation → execute → verify.127128**Never run any command that modifies system state without explicit user confirmation.**129130Read **`flow_fix.md`** for: safety rules, per-fix protocol, batch mode, scope limits.131Reference **`fix_cases.md`** for proven fix steps, rollback commands, and prevention strategies.132133---134135## Phase 6 — Fix Summary136137After fix cycle, generate a final summary: actions taken, score changes, remaining issues.138Append fix results to the previously generated report files.139140Read **`flow_summary.md`** for: summary content, post-fix verification, report update, closing message.141142---143144## Key Constraints1451461. **Scripts First** — Use `scripts/collect-*.sh` for structured data; read files directly for raw content.1472. **Evidence-Based** — Every finding must cite the specific `DATA.<key>.<field>` and its actual value.1483. **Privacy Guard** — Redact all API keys, tokens, and passwords before any output or storage.1494. **Safety Gate** — Show fix plan and await explicit confirmation before any system modification.1505. **Language Rule** — Instructions in this file are in English. All output to the user must be in REPORT_LANG.
jsgforever