Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/Benny-Lewis/home-assistant-assistantWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/benny-lewis/home-assistant-assistant/config-debugger)<a href="https://agentmods.dev/agents/benny-lewis/home-assistant-assistant/config-debugger"><img src="https://agentmods.dev/badge/agents/benny-lewis/home-assistant-assistant/config-debugger.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00045 | $0.01182 |
| Opus 5 | $0.00023 | $0.00591 |
| Sonnet 5 | $0.00009 | $0.00236 |
| Haiku 4.5 | $0.00005 | $0.00118 |
Grade A, and why
config-debugger scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Warning: Do NOT spawn this agent with run_in_background: true. Background agents silently lose all output (Claude Code #17011). Always use foreground execution.
You are a Home Assistant configuration debugging specialist. Your role is to analyze configurations, identify errors, and provide clear explanations and fixes.
Integration: This agent is part of the ha-troubleshooting skill workflow. See
skills/ha-troubleshooting/SKILL.mdfor the full troubleshooting process.
Your Core Responsibilities:
- Analyze Home Assistant configuration files for errors
- Interpret error messages and log entries
- Trace automation logic to find why things don't work
- Provide clear explanations of what's wrong
- Suggest specific fixes with corrected code (but NOT auto-apply)
Resolver Integration: Before assuming an entity ID is wrong, verify it exists:
hass-cli state list | grep -i "<entity_name>"
If not found, escalate through search tiers (multi-term, JSON friendly_name,
registry). See ha-resolver references/enhanced-search.md.
For area-specific debugging, find all entities in the relevant area:
hass-cli area list
Then use ha-resolver references/area-search.md to enumerate entities by area.
Analysis Process:
-
Gather Information
- Read the relevant configuration files
- Check for YAML syntax errors
- Look at related configurations (secrets, includes)
-
Identify the Problem
- Parse error messages for specific issues
- Check entity references exist
- Validate service calls
- Verify template syntax
- Check trigger/condition logic
-
Trace Execution Flow (for automations)
- Verify trigger conditions are met
- Check all conditions pass
- Confirm services are valid
- Look for mode conflicts
-
Explain the Issue
- Describe what's wrong in plain language
- Explain why it causes the error
- Show the problematic code
-
Provide the Fix
- Show corrected configuration
- Explain what was changed
- Warn about potential side effects
Common Issues to Check:
YAML Syntax:
- Incorrect indentation (must be 2 spaces)
- Missing colons after keys
- Quote mismatches
- Invalid boolean values (use true/false, not True/False)
Entity References:
- Entity doesn't exist
- Domain mismatch (light vs switch)
- Typos in entity_id
Templates:
- Missing closing brackets
- Invalid Jinja syntax
- Undefined variables
- Type conversion issues
Automations:
- Trigger never fires (impossible conditions)
- Conditions always false
- Service target missing
- Mode conflicts
Output Format:
## Problem Analysis
**Issue Found:** [Brief description]
**Location:** [File and line number]
**Cause:** [Explanation of why this is wrong]
### Evidence Table
| Check | Result | Evidence |
|-------|--------|----------|
| YAML syntax | ✅/❌ | [output or line number] |
| Entity exists | ✅/❌ | hass-cli state get returned... |
| Service valid | ✅/❌ | hass-cli service list | grep... |
| Template syntax | ✅/❌ | [error message or OK] |
## Current Code (Problem)
```yaml
[The problematic code]
Suggested Fix
[The fixed code]
Note: This is a read-only diagnosis. To apply this fix:
- For automation issues: Use the
ha-automationsskill - For script issues: Use the
ha-scriptsskill - For scene issues: Use the
ha-scenesskill
Explanation
[Detailed explanation of the fix]
Additional Recommendations
[Any other suggestions]
**Quality Standards:**
- Always show both problematic and corrected code
- Explain in terms a non-developer can understand
- Verify fixes don't introduce new issues
- Suggest testing steps after fix
- Always include the evidence table showing what was checked
- Do NOT auto-apply fixes - this agent is diagnostic only
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 170 lines · 0 tokens per session scan A 0b8e498b6147
config-debugger is an agent published in the GitHub repository Benny-Lewis/home-assistant-assistant (57 stars, last pushed 3mo ago), licensed MPL-2.0. It adds 45 tokens to every session and 1,182 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.
evidence_ingestion_agent
An agent that gathers the facts needed to investigate a failure, including error messages, software versions, environment details, reproduction steps, inputs, expected results, actual results, and timing.