Skip to content
Agentmart
Submit a tool

healer

Healer monitoring expertise - detection patterns, API endpoints, dual-model architecture, and remediation workflows.

Skill by 5DLabsInc

IndexedAGPL-3.0
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/5dlabsinc-healer

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Healer monitoring expertise - detection patterns, API endpoints, dual-model architecture, and remediation workflows. Use when monitoring Play workflows or debugging agent failures.

Use cases: backend, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/healer

What's inside

Skill name
healer
Description
Healer monitoring expertise - detection patterns, API endpoints, dual-model architecture, and remediation workflows. Use when monitoring Play workflows or debugging agent failures.
License
AGPL-3.0
Instructions
195 lines in SKILL.md · view on GitHub

Before installing

  • Instructions call the network

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Healer Skill

Healer is the observability and self-healing layer for CTO Play workflows. It monitors pod logs via Loki, detects issues, and orchestrates remediations.

## When to Use

- Monitoring Play workflow execution
- Debugging agent failures (pre-flight, runtime)
- Understanding detection patterns (A10, A11, A12)
- Checking session status

---

## Healer API Endpoints

| Endpoint | Method | Purpose |
|----------|--------|---------|
| `/health` | GET | Health check |
| `/api/v1/session/start` | POST | MCP calls this on play() |
| `/api/v1/session/{play_id}` | GET | Get session details |
| `/api/v1/sessions` | GET | List all sessions |
| `/api/v1/sessions/active` | GET | List active sessions only |

### Check Active Sessions

```bash
curl http://localhost:8083/api/v1/sessions/active | jq
```

---

## Detection Patterns

### Priority 1: Pre-Flight Failures (within 60s of agent start)

| Pattern | Alert Code | Meaning |
|---------|-----------|---------|
| `tool inventory mismatch` | A10 | Agent missing declared tools |
| `Tool inventory MISMATCH` | A10 | Specific tool unavailable |
| `declared tools.*missing` | A10 | Tools in config not in CLI |
| `cto-config.*(missing\|invalid)` | A11 | Config not loaded/synced |
| `mcp.*failed to initialize` | A12 | MCP server init failure |
| `tools-server.*unreachable` | A12 | Tools-server down |

### Priority 2: Runtime Failures

| Pattern | Severity | Action |
|---------|----------|--------|
| `panicked at`, `fatal error` | Critical | Immediate escalation |
| `timeout`, `connection refused` | High | Infrastructure issue |
| `max retries exceeded` | High | Agent exhausted attempts |
| `permission denied.*filesystem` | Critical | Can't read/write files |
| `unauthorized\|invalid token` | Critical | Auth broken |

### Priority 3: Lifecycle Issues

| Pattern | Meaning |
|---------|---------|
| `template not found` | Prompt template missing |
| `prompt.*missing` | Agent instructions not loaded |
| `role.*undefined` | Agent role not set |
| `task context.*empty` | Task details not injected |

---

## Dual-Model Architecture

```
┌─────────────────────────────────────────────────────────────────────────────┐
│                        DUAL-MODEL HEALER ARCHITECTURE                        │
│                                                                              │
│   DATA SOURCES                                                              │
│   ├─ Loki (all pod logs)                                                    │
│   ├─ Kubernetes (CodeRuns, Pods, Events)                                    │
│   ├─ GitHub (PRs, comments, CI status)                                      │
│   └─ CTO Config (expected tools, agent settings)                            │
│                              │                                               │
│                              ▼                                               │
│   MODEL 1: EVALUATION AGENT                                                 │
│   ├─ Parses and comprehends ALL logs                                        │
│   ├─ Correlates events across agents                                        │
│   ├─ Identifies root cause                                                  │
│   └─ Creates GitHub Issue with analysis                                     │
│                              │                                               │
│                              ▼                                               │
│   MODEL 2: REMEDIATION AGENT                                                │
│   ├─ Reads the GitHub issue                                                 │
│   ├─ Implements the fix                                                     │
│   ├─ Creates PR with changes                                                │
│   └─ Marks issue resolved                                                   │
└─────────────────────────────────────────────────────────────────────────────┘
```

---

## Session Notification Flow

```
MCP play() call
    │
    ▼
POST /api/v1/session/start
    │
    └─ Payload: {
         play_id,
         repository,
         cto_config: { agents, tools },
         tasks: [...]
       }
    │
    ▼
Healer stores session with expected tools per agent
    │
    ▼
CodeRuns start with Healer already aware
```

---

From 5DLabsInc/cto, AGPL-3.0.

More from 5DLabsInc/cto

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Apr 26, 2026 (6 months ago)
Last release
May 31, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
AGPL-3.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from 5DLabsInc

Cite this page

healer skill. Agent Mart. https://agentmart.dev/skills/5dlabsinc-healer (last updated 2026-10-24)