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/deephaven/deephaven-mcp/ref-cli-tool-wrappingnpx skills add deephaven/deephaven-mcp --skill ref-cli-tool-wrappinggit clone --depth 1 https://github.com/deephaven/deephaven-mcpWhat 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 | $0.00074 | $0.03944 |
| Opus 5 | $0.00037 | $0.01972 |
| Sonnet 5 | $0.00015 | $0.00789 |
| Haiku 4.5 | $0.00007 | $0.00394 |
Grade A, and why
ref-cli-tool-wrapping 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.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI tool-wrapping conventions
Runtime dhcli commands (session, system, table, catalog, pq, docs) wrap MCP tools. This skill is the how; the why is docs/design/CLI_TOOL_WRAPPING.md. cli-command-add loads it for any wrapper verb and supplies the general click/Pattern-B/error conventions; this skill adds the wrapper-specific concern. Apply ref-cli-help-standards for the help contract. It does not apply to daemon/config (not tool wrappers) or to MCP server tools themselves (ref-mcp-module-organization).
The shared flow
Every daemon-backed wrapper routes through cli/_commands/_wrapping.py, never a hand-rolled daemon/MCP dance (a direct-URL wrapper — category 5 below — skips the acquire flow but still reuses _wrapping.py's fetch/render pieces). Two top-level helpers cover the two output shapes; neither drops a partial-but-successful result's diagnostic siblings (the partial_result block from enterprise-session discovery, and a truncating tool's is_complete: false flag) — the whole-payload helper carries them in the stdout envelope, the shaping helper re-surfaces them on stderr:
call_and_echo(runtime, "<tool>", *, retry_command, arguments)— whole-payload verb: emit the tool's success payload as-is on stdout (the envelope carries any diagnostics).call_and_echo_field(runtime, "<tool>", *, retry_command, arguments, field, default)— shaping verb: emit one payload field (e.g. alistverb's array) on stdout, and surface diagnostic siblings on stderr. For a truncating tool, passtruncation_hint="Raise --max-rows or narrow with --filter."(naming the verb's own flags) to extend the genericis_complete: falsewarning. Use this instead of hand-rollingcall_for_payload+echo_payload, which would drop the diagnostics.
# Whole-payload verb (emit the tool's result as-is):
await call_and_echo(
runtime, "<tool>", retry_command="dhcli <noun> <verb>", arguments=arguments
)
# Shaping verb (emit one field as a bare value):
await call_and_echo_field(
runtime, "<tool>", retry_command="dhcli <noun> <verb>",
arguments=arguments, field="<key>", default=[],
)
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 · 125 lines · 74 tokens per session scan A 5c8cd89a250b
ref-cli-tool-wrapping is a skill published in the GitHub repository deephaven/deephaven-mcp (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 74 tokens to every session and 3,944 once invoked, about $0.0004 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
mcporter
List, auth, and call MCP servers/tools from the terminal.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…
mcp-scripting
Write mcpScript JavaScript for discovering, inspecting, and calling MCP tools.