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-documentation-rolesnpx skills add deephaven/deephaven-mcp --skill ref-documentation-rolesgit 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/ref-documentation-roles)<a href="https://agentmods.dev/skills/deephaven/deephaven-mcp/ref-documentation-roles"><img src="https://agentmods.dev/badge/skills/deephaven/deephaven-mcp/ref-documentation-roles.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.02573 |
| Opus 5 | $0.00026 | $0.01287 |
| Sonnet 5 | $0.00010 | $0.00515 |
| Haiku 4.5 | $0.00005 | $0.00257 |
Grade A, and why
ref-documentation-roles 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 3d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Roles
Every top-level markdown file in this repository has a single, intentional role. Edits must respect that role. This skill is the canonical source of truth for those roles; the docs workflows (docs-improve, docs-accuracy) and cli-command-add load it before making changes.
Roles
| File | Reader | In scope | Out of scope |
|---|---|---|---|
README.md |
end user (not developer) | Get a user installed, configured, and connected to their AI tool with minimum friction. Quick start, install (including extras), upgrade path, AI-tool setup, capability list (one line per tool), troubleshooting, architecture overview. | Detailed schema reference, per-tool reference detail, internal mechanics, contributor workflows. |
docs/CONFIGURATION.md |
operator | Configuration files and directories — schema, fields, defaults, templating syntax. | Install options (uv extras, pip), security narrative, developer workflows, the v1→v2 migration procedure (lives in MIGRATION.md). |
docs/MIGRATION.md |
end user upgrading from v1 (not developer) | One-time v1→v2 configuration conversion, end-user friendly: running the converter, its CLI options, where it writes, and how to act on warnings. | Steady-state config schema/fields/defaults (lives in CONFIGURATION.md); package/tool upgrade commands (live in README's "Quick Upgrade"); templating syntax. |
docs/ENV.md |
operator | The canonical inventory of every environment variable any binary reads — both servers and the dhcli CLI. One entry per variable: which binary reads it, accepted values, precedence, and the cli.json / server.json field it corresponds to. |
Templating syntax (lives in CONFIGURATION.md), uv. |
docs/SECURITY.md |
operator deploying the server | Short, self-contained guide. A reader must be able to stand up a secure deployment without leaving the page. Trust model, hardening checklist, authentication, transport security, secret handling, rotation. | Anything that requires bouncing to DEVELOPER_GUIDE.md to act on. |
docs/UV.md |
developer new to uv |
Generic uv crash course. |
Project-specific commands, project env vars, project tests, project install lines. |
docs/CLI.md |
operator + AI agent using the local dhcli CLI |
Full dhcli reference: command surface (noun-verb tree), global flags, env-var bindings, exit codes, error_code registry, output modes (human / json / json-pretty / yaml), examples, shell completion, dhcli agents self-discovery (the --agents flag and summary tree). |
Server-side configuration (lives in CONFIGURATION.md); developer/contributor mechanics (lives in DEVELOPER_GUIDE.md); the env-var inventory (ENV.md owns it). CLI.md documents each CLI env binding — which flag maps to which variable — and links to ENV.md for the entry. |
docs/DEVELOPER_GUIDE.md |
contributor | Everything a developer working on the project needs. Catch-all. | Per-tool reference (parameters, returns, examples) — see Tool reference is owned by code. |
docs/STANDALONE_BINARIES.md |
anyone building, installing, or deploying the standalone binaries (not just contributors) | Self-contained, end-to-end: installing a prebuilt binary (download, extract, point an AI tool at it) and building/releasing them (prerequisites including the Rust/PyApp setup needed to build, build commands, output artifacts, supported platforms, the CI release workflow). README's install section is a one-line pointer here, not a parallel copy. | Project-maintainer minutiae (e.g. bumping pinned-version source constants); server configuration schema (lives in CONFIGURATION.md, linked); per-tool reference (lives in code docstrings). |
docs/design/*.md |
contributor / architect | Design rationale for a subsystem — the why behind a structural decision (trade-offs weighed, chosen approach, invariants). One file per subsystem; e.g. docs/design/CLI_TOOL_WRAPPING.md. |
Per-command / per-API reference (lives in docs/CLI.md or the code); step-by-step contributor workflow (lives in DEVELOPER_GUIDE.md). |
CONTRIBUTING.md |
prospective contributor | How to submit work: getting the source, opening a pull request (web and gh CLI), and the CLA requirement. |
Build, test, and code-quality mechanics (live in DEVELOPER_GUIDE.md); coding standards (owned by ref-python-coding-practices). |
AGENTS.md |
AI agent | Agent process rules. Not human documentation; no TOC. | Anything intended for humans. |
CLAUDE.md |
Claude Code (agent) | A wiring shim only: an @AGENTS.md import so Claude Code loads the same rules. Keep it to that one line. |
Any rule content — it belongs in AGENTS.md. The cross-agent wiring contract is owned by ref-skill-authoring-standards Cross-agent portability. |
CODE_OF_CONDUCT.md |
community participant | Upstream Contributor Covenant boilerplate, adopted unmodified. | Everything — do not edit this file to suit a project need; it is not a project-authored document. |
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.
- 3d ago First seen · 68 lines · 52 tokens per session scan A cc12199ebcfc
ref-documentation-roles is a skill published in the GitHub repository deephaven/deephaven-mcp (5 stars, last pushed 6d ago), licensed Apache-2.0. It adds 52 tokens to every session and 2,573 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…