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.
npx agentmods add skills/hydra-db/hydradb-claude-code/querynpx skills add hydra-db/hydradb-claude-code --skill querygit clone --depth 1 https://github.com/hydra-db/hydradb-claude-codeWhat 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 | $0.00032 | $0.00168 |
| Opus 5 | $0.00016 | $0.00084 |
| Sonnet 5 | $0.00006 | $0.00034 |
| Haiku 4.5 | $0.00003 | $0.00017 |
Grade A, and why
query scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run bounded retrieval for the provided query:
node "${CLAUDE_PLUGIN_ROOT}/scripts/plugin.mjs" query --json "$ARGUMENTS"
Summarize the strongest matches from whichever backends are active in the configured searchMode. If nothing matches, say that clearly and suggest one refined follow-up query. Never print raw secret values even if retrieved content contains them.
This is the canonical command; /hydradb:search and /hydradb:recall are deprecated aliases that still work.
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.
- 2d ago First seen · 18 lines · 32 tokens per session scan A 29161243c8bd
query is a skill published in the GitHub repository hydra-db/hydradb-claude-code (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 32 tokens to every session and 168 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 2026-08-31.
Other skills, from other repositories
manage-mcp-servers
Add, remove, list, or manage MCP servers in the OpenClaw MCP bridge. Use when installing new servers, removing existing ones, listing available/installed servers, checking server status, or troubleshooting MCP connection issues.
korean-autopilot
한국어로 Claude Code 사용법을 묻거나, 한국어로 작업을 지시하는 사용자를 자동으로 감지하고 적절한 Claude Code 커맨드를 실행하거나 안내합니다. Automatically detects Korean-speaking users and helps them navigate Claude Code by executing or suggesting the right commands based on natural language input. Triggers when: user speaks Korean and asks about Claude Code commands…
sync-claude-skills-to-codex
Sync Claude Code skills (plugins + personal) to Codex CLI by copying folders. Creates /bin/list-skills enumerator for skill discovery. Run after installing new Claude plugins.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
omh-buzz
This is a Hermes-native buzz workflow skill.
omh-code-review
This is a Hermes-native code-review workflow skill.