# hippo_skill_health

FORGIA #216 — per-skill diagnostic. Returns

Agent View of the PolicyLayer registry record for `hippo_skill_health`. HTML page: https://policylayer.com/tools/verimem/hippo-skill-health

## Facts

- Tool: `hippo_skill_health`
- Server: Verimem (`aureliocpr-ctrl/verimem`) — https://policylayer.com/tools/verimem.md
- Homepage: https://github.com/aureliocpr-ctrl/verimem
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "hippo_skill_health",
    "arguments": {}
  }
}
```

## Why hippo_skill_health is rated Low

This tool appears to perform diagnostics on individual skills and return status or health metrics. Diagnostics are inherently observational (Read category) with no side effects. The server's focus on trusted memory and measurement supports a non-destructive, non-mutating operation. There is no evidence of code execution, data modification, deletion, or financial operations.

From the tool's own definition: "Tool name 'hippo_skill_health' and description indicating it 'Returns' diagnostic information suggests data retrieval. No mutation, deletion, execution, or financial operations are indicated."

## Use case

AI agents call hippo_skill_health to retrieve information from Verimem without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Verimem:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "hippo_skill_health": {}
  }
}
```

## Other tools on Verimem (236)

- `hippo_fact_forget` — Destructive — https://policylayer.com/tools/verimem/hippo-fact-forget.md
- `hippo_fact_forget_with_undo` — Destructive — https://policylayer.com/tools/verimem/hippo-fact-forget-with-undo.md
- `hippo_forget` — Destructive — https://policylayer.com/tools/verimem/hippo-forget.md
- `hippo_forget_scope` — Destructive — https://policylayer.com/tools/verimem/hippo-forget-scope.md
- `hippo_skill_archive` — Destructive — https://policylayer.com/tools/verimem/hippo-skill-archive.md
- `hippo_skill_retire` — Destructive — https://policylayer.com/tools/verimem/hippo-skill-retire.md
- `hippo_compose_plan` — Execute — https://policylayer.com/tools/verimem/hippo-compose-plan.md
- `hippo_consolidate` — Execute — https://policylayer.com/tools/verimem/hippo-consolidate.md
- `hippo_curate_pipeline` — Execute — https://policylayer.com/tools/verimem/hippo-curate-pipeline.md
- `hippo_decay_run` — Execute — https://policylayer.com/tools/verimem/hippo-decay-run.md
- `hippo_plan_strips` — Execute — https://policylayer.com/tools/verimem/hippo-plan-strips.md
- `hippo_provider_switch` — Execute — https://policylayer.com/tools/verimem/hippo-provider-switch.md
- `hippo_reason` — Execute — https://policylayer.com/tools/verimem/hippo-reason.md
- `hippo_rollout_actions` — Execute — https://policylayer.com/tools/verimem/hippo-rollout-actions.md
- `hippo_run_task` — Execute — https://policylayer.com/tools/verimem/hippo-run-task.md
- `hippo_skill_compile_macro` — Execute — https://policylayer.com/tools/verimem/hippo-skill-compile-macro.md
- `hippo_skill_derive_predicates` — Execute — https://policylayer.com/tools/verimem/hippo-skill-derive-predicates.md
- `hippo_skills_derive_predicates_batch` — Execute — https://policylayer.com/tools/verimem/hippo-skills-derive-predicates-batch.md
- `hippo_world_simulate` — Execute — https://policylayer.com/tools/verimem/hippo-world-simulate.md
- `sandbox_exec` — Execute — https://policylayer.com/tools/verimem/sandbox-exec.md
- `hippo_dream_propose` — Other — https://policylayer.com/tools/verimem/hippo-dream-propose.md
- `hippo_agent_specialization` — Read — https://policylayer.com/tools/verimem/hippo-agent-specialization.md
- `hippo_agent_workload` — Read — https://policylayer.com/tools/verimem/hippo-agent-workload.md
- `hippo_anchor_recall` — Read — https://policylayer.com/tools/verimem/hippo-anchor-recall.md
- `hippo_anti_confab_scan` — Read — https://policylayer.com/tools/verimem/hippo-anti-confab-scan.md
- `hippo_assess_confidence` — Read — https://policylayer.com/tools/verimem/hippo-assess-confidence.md
- `hippo_assess_fact_freshness` — Read — https://policylayer.com/tools/verimem/hippo-assess-fact-freshness.md
- `hippo_audit_summary` — Read — https://policylayer.com/tools/verimem/hippo-audit-summary.md
- `hippo_audit_tail` — Read — https://policylayer.com/tools/verimem/hippo-audit-tail.md
- `hippo_briefing` — Read — https://policylayer.com/tools/verimem/hippo-briefing.md
- …and 206 more: https://policylayer.com/tools/verimem.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=verimem · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/verimem