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-help-standardsnpx skills add deephaven/deephaven-mcp --skill ref-cli-help-standardsgit 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 | $0.00058 | $0.03927 |
| Opus 5 | $0.00029 | $0.01963 |
| Sonnet 5 | $0.00012 | $0.00785 |
| Haiku 4.5 | $0.00006 | $0.00393 |
Grade A, and why
ref-cli-help-standards 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI Help Standards
The dhcli CLI is described by three surfaces from two authored sources: in-code help renders both the --help text and the agents-manifest node — a HelpSpec on the root and every leaf command, a function docstring on each noun group (split into manifest summary/description by _split_help_text; see Help-content contract, Group commands) — and docs/CLI.md is written by hand. Help text is plain text rendered verbatim by click in the terminal, so it carries no reStructuredText markup. Every leaf command's help follows a fixed section contract so a human or an AI agent can operate the command without reading the source or docs/CLI.md.
1. Three surfaces, two sources
| Surface | Role | Canonical source | Edited via |
|---|---|---|---|
docs/CLI.md |
Exhaustive reference | docs/CLI.md |
docs-improve / docs-accuracy (ref-documentation-roles) |
--help text |
Self-sufficient per-command help | the command's HelpSpec (cli/_help.py, rendered by build_help) |
cli-help-improve / cli-help-accuracy |
| agents manifest | Machine surface for agents (--help for AI agents) |
the same HelpSpec (cli/_manifest.py: build_summary_tree, build_manifest, describe_command); wired into commands by cli/_commands/agents.py |
cli-help-improve / cli-help-accuracy |
Consistency rule. --help and the agents manifest render from the one HelpSpec, so they cannot drift from each other — the surface to reconcile by hand is docs/CLI.md: a command's flags, arguments, exit codes, error_codes, and output fields must match between the spec and the doc. Change one, update the other in the same edit. The contract tests in tests/cli/test_help_contract.py (per-command section coverage, parametrized over the live click tree), tests/cli/test__help.py (build_help rendering), and tests/cli/test__manifest.py (the manifest builders: cleanliness, node schema, content preservation) pin the spec side; tests/cli/_commands/test_agents.py pins the agents verbs' CLI behavior (output modes, config bypass, flag/verb equivalence). docs/CLI.md has no automated check — verify it by hand.
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 · 103 lines · 58 tokens per session scan A 947c025cdbe5
ref-cli-help-standards is a skill published in the GitHub repository deephaven/deephaven-mcp (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 58 tokens to every session and 3,927 once invoked, about $0.0003 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…