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/docs-improvenpx skills add deephaven/deephaven-mcp --skill docs-improvegit 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 | $0.00065 | $0.00571 |
| Opus 5 | $0.00032 | $0.00285 |
| Sonnet 5 | $0.00013 | $0.00114 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
docs-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 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use this vs. docs-accuracy: use docs-improve for a full review (accuracy + reorganization + missing content + formatting). Use docs-accuracy for surgical correctness-only fixes when the doc's structure is already sound.
Before doing anything
Load ref-documentation-roles — the canonical source for each document's role and the editing rules that follow from it (in-scope content stays; out-of-scope content relocates rather than being rewritten in place; self-contained vs. generic docs; the cross-reference policy). Evaluate every proposed change against the target document's role; if a change would violate it, stop and reconsider before editing.
Steps
Create a plan for improving this markdown file, then execute it.
- Confirm the document's role per
ref-documentation-roles. Note any sections currently out of scope; plan to relocate them, not rewrite them in place. - Look for content that is missing from this file for its role and needs to be added. Use the source code as a reference. If there is a conflict, the source code should be believed over the markdown.
- Apply the
docs-accuracyskill. - Draft the target section outline for this document's role: one section per in-scope responsibility, ordered along the reader's path through the task. Produce the outline as an explicit list before editing.
- Reorganize the sections to match the outline from step 4; every section's content stays within the document's role.
- Make sure that all referenced files and paths have hyperlinks.
- Check all of the links in the document to make sure they are correct.
- Link every product, website, or service the document references to its canonical URL.
- Apply the
ref-markdown-documentation-standardsskill for formatting compliance (including the Table of Contents requirement). - Final residual-check pass. Walk the document end-to-end one more time against the role from step 1; list any remaining bullets where you can name a concrete defect (out-of-scope content, missing example, broken link, stale fact, ambiguous instruction). If you cannot name a concrete defect, the doc is done — stop. Vague "could be improved" feelings are not findings.
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 · 28 lines · 65 tokens per session scan A c7752e2f6945
docs-improve is a skill published in the GitHub repository deephaven/deephaven-mcp (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 65 tokens to every session and 571 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…