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 instructions/deephaven/deephaven-mcp/agents-mdgit 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 | $0.03251 | $0.03251 |
| Opus 5 | $0.01625 | $0.01625 |
| Sonnet 5 | $0.00650 | $0.00650 |
| Haiku 4.5 | $0.00325 | $0.00325 |
Grade A, and why
deephaven-mcp AGENTS.md 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deephaven MCP — Agent Guidelines
Testing
- Always use
uv run pytestinstead ofpytestdirectly. This ensures the correct virtual environment and dependencies are used. - Target 100% per-source-file coverage. Apply
tests-improveto bring a file up to target.
Timeouts
These operations are slow by nature, not hung — set generous timeouts:
uv pip install/uv sync/ anyuvpackage operation: allow at least 120 seconds../bin/precommit.sh: allow at least 60 seconds (~22 seconds typical).uv run pytest(full suite): allow at least 120 seconds.uv run mypy src/: allow at least 30 seconds (~15 seconds typical).
Version Control
- When moving or renaming files, use
git mvrather than delete + create. When removing files, usegit rm. Preserving history matters. - Never stage or commit. Do not run
git add,git commit,git reset, or anything else that mutates the index or history unless the USER explicitly requests that exact operation. The USER reviews and stages every change personally; staging on their behalf destroys partial-review state (e.g., hunks staged withgit add -p) irrecoverably. Thegit mv/git rmrule above is the sole carve-out, and only for the files the task itself moves or removes. When work is done, leave all changes unstaged and report.
Scope discipline
- Adding a user-visible surface — environment variable, config field, CLI flag, error code, output field, MCP tool, or any other user-visible contract — requires an explicit request or an approved plan. Propose it and wait; never introduce one as a side effect of another task. Each is a contract that gets documented, tested, and is costly to withdraw once shipped.
- Carve-out for entailed surfaces: a surface the approved change requires is in scope. A requested command brings its flags, its error codes, and its output fields; a requested config field brings its key. What needs approval is a surface that stands on its own, not the parts the request already implies.
- Environment variables are the most-violated case:
docs/ENV.mdis the canonical inventory and every entry in it is deliberate. Applyref-configuration-conventionsbefore changing env-var behavior, pluscli-command-addfor CLI code.
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 · 81 lines · 3,251 tokens per session scan A e96091450872
deephaven-mcp AGENTS.md is an instructions file published in the GitHub repository deephaven/deephaven-mcp (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 3,251 tokens to every session, about $0.0163 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.