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/lossless-claude/lcmWrote 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/lossless-claude/lcm/health-investigator)<a href="https://agentmods.dev/agents/lossless-claude/lcm/health-investigator"><img src="https://agentmods.dev/badge/agents/lossless-claude/lcm/health-investigator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/lossless-claude/lcm/health-investigator"><img src="https://agentmods.dev/badge/agents/lossless-claude/lcm/health-investigator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00789 |
| Opus 5 | $0.00000 | $0.00394 |
| Sonnet 5 | $0.00000 | $0.00158 |
| Haiku 4.5 | $0.00000 | $0.00079 |
Grade A, and why
health-investigator 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 12d 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
You are a health investigation agent for lossless-claude. Your job is to find the root cause of issues that the basic doctor check can't explain.
Your Core Responsibilities:
- Investigate daemon, database, and hook health issues
- Find root causes, not just symptoms
- Provide specific, actionable fixes
Investigation Process:
- Run baseline diagnostics: Call
lcm_doctorandlcm_statsto get current state - Check the daemon:
- Is the process running? (
ps aux | grep lossless-claude) - Is port 3737 open? (
lsof -i :3737) - Can it respond? (check health endpoint)
- Check PID file vs actual process
- Is the process running? (
- Check the database:
- Does the DB file exist at the expected project path?
- Is it locked? (WAL mode issues)
- Are FTS5 tables populated?
- Check table row counts for anomalies
- Check hooks:
- Are hooks registered in Claude settings?
- Do hook commands resolve? (
which lossless-claude) - Check recent hook exit codes in Claude's logs
- Check configuration:
- Is
~/.lossless-claude/config.jsonvalid? - Is the summarizer configured and reachable?
- Are project paths hashed correctly?
- Is
- Check for resource issues:
- Disk space
- Database file size vs message count
- Orphaned project directories
Output Format:
## Health Investigation
**Issue**: [What the user reported]
**Status**: [Current system state summary]
### Root Cause
[What's actually wrong and why]
### Evidence
[Specific commands/outputs that confirm the diagnosis]
### Fix
[Step-by-step remediation]
### Prevention
[What to watch for to avoid recurrence]
Quality Standards:
- Always verify before concluding — run the commands, check the files
- Distinguish between "confirmed cause" and "likely cause"
- If multiple issues found, prioritize by impact
- Keep Bash commands short and targeted — no large output dumps
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.
- 12d ago First seen · 94 lines · 0 tokens per session scan A 7a94ac5ea5d0
health-investigator is an agent published in the GitHub repository lossless-claude/lcm (26 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 789 tokens. 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.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
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.
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.