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/cli-help-accuracynpx skills add deephaven/deephaven-mcp --skill cli-help-accuracygit 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 | $0.00080 | $0.00724 |
| Opus 5 | $0.00040 | $0.00362 |
| Sonnet 5 | $0.00016 | $0.00145 |
| Haiku 4.5 | $0.00008 | $0.00072 |
Grade A, and why
cli-help-accuracy 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use this vs. cli-help-improve: use cli-help-accuracy for surgical correctness-only fixes when the help structure is already complete. Use cli-help-improve for a full review that may add missing sections, single-source the output schema, or reconcile all three surfaces.
Before doing anything
Load ref-cli-help-standards. --help and the agents manifest both render from the command's HelpSpec, so fixing the spec fixes both; docs/CLI.md is authored separately and must be reconciled by hand. Fixing an inaccuracy in the spec without the doc (or vice versa) reintroduces drift, so check and fix both together.
Verify every claim against the handler
For each command in scope, read the handler and confirm:
- Options and arguments — every documented flag/argument exists with the stated name, type, default, and effect; every actual option has a
help=;show_default=Truewhere there is a default. No documented flag is missing from the code, and no code flag is undocumented. - Error codes — the
error_codes=block lists exactly theerror_codes the command can raise. Trace eachCliError(code=...)in the handler and in any shared helper it calls (e.g.acquire_daemonraisesdaemon_startup_timeout/daemon_reuse_refused/daemon_not_running/daemon_registry_corrupt). No phantom codes; no missing ones. - Exit codes — the documented numeric codes match reality. Every
CliErrorexits2exceptErrorCode.TOOL_RETURNED_ERROR, the sole code whoseexit_codeis3; the exit code is carried by theErrorCode, not aCliErrorparameter (there is noexit_code=argument). - Output fields — every
OutputFieldnames a real key in theformat_output(...)payload, with the correct type; themode(object/list/text) matches what is printed. TheOutputSpecconstant is passed once, as the spec'soutput=field (single source — never two literals that can drift). Each field'shelpstring must accurately describe the value vocabulary the code emits — applyref-output-serialization-conventions. - Examples — each example command is runnable and uses real flags/args;
jqfilters reference real output keys. - Plain text — no double-backtick literals or
:func:/:class:markup in any surfaced string.
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 · 30 lines · 80 tokens per session scan A 646e39f6ffaf
cli-help-accuracy is a skill published in the GitHub repository deephaven/deephaven-mcp (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 80 tokens to every session and 724 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…