Borrowing it
Nothing to install: this file belongs to deephaven/deephaven-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/deephaven/deephaven-mcp/main/.agents/skills/cli-help-improve/SKILL.mdgit clone --depth 1 https://github.com/deephaven/deephaven-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/deephaven/deephaven-mcp/cli-help-improve)<a href="https://agentmods.dev/skills/deephaven/deephaven-mcp/cli-help-improve"><img src="https://agentmods.dev/badge/skills/deephaven/deephaven-mcp/cli-help-improve/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/deephaven/deephaven-mcp/cli-help-improve"><img src="https://agentmods.dev/badge/skills/deephaven/deephaven-mcp/cli-help-improve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00072 | $0.00793 |
| Opus 5.5 | $0.00029 | $0.00317 |
| Sonnet 5.5 | $0.00014 | $0.00159 |
| Haiku 4.5 | $0.00007 | $0.00079 |
Grade A, and why
cli-help-improve 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 1mo 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use this vs. cli-help-accuracy: use cli-help-improve for a full review (accuracy + missing sections + output single-sourcing + reconciling all three surfaces). Use cli-help-accuracy for surgical correctness-only fixes when the help structure is already complete.
Before doing anything
Load ref-cli-help-standards — it is the contract this skill enforces. Identify the target: a single command module under cli/_commands/, or the whole CLI. For each command, the surfaced help (the command's HelpSpec, every click.option(help=...), group docstrings) is in scope; internal docstrings are not (those are pydocs-improve's job).
Steps
For each command in scope:
- Read the handler. Determine what the command actually does, every positional argument and option, every
CliError(code=...)it raises (directly or via a shared helper likeacquire_daemon), the exit codes it can return, and the exact shape of what it prints (format_output(...)payload). - Check section coverage against
ref-cli-help-standardsHelp-content contract. Add any missing section via the command'sHelpSpec: Summary, Description (with side effects), Arguments, Output, Examples (one human + one agent), See also, Exit codes, Error codes. Drop a section only when genuinely not applicable (no positional args → no Arguments; pure discovery command → no Error codes). - Single-source the output (Output is single-source). Define one
OutputSpecconstant; pass it as the spec'soutput=field (output_specderives from it). EachOutputField(name, type, help)must name a real key in the printed payload. Free-form output usesmode="text"with empty fields. - Apply
cli-help-accuracyto the command — every documented flag, argument, error code, exit code, and output field must match the code. - Strip RST (Plain text, not reStructuredText) from every surfaced string: no double-backtick literals, no
:func:/:class:roles. Use single quotes for inline literals. - Reconcile the third surface. Update the command's entry in
docs/CLI.mdso flags, arguments, exit codes, error codes, and output fields agree.docs/CLI.mdhas no automated check — verify by hand (applydocs-accuracyfor that file). - Verify per the standard's Verify section: render
--help, inspect the agents node (params + error codes + output, no double-backtick literals or\b), and run the contract tests.
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.
- 1mo ago First seen · 33 lines · 72 tokens per session scan A 14cc6b02448b
cli-help-improve is a skill published in the GitHub repository deephaven/deephaven-mcp (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 72 tokens to every session and 793 once invoked, about $0.0003 per session on Opus 5.5. 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…