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/jamesdsizemore/rush-cli/agents-mdgit clone --depth 1 https://github.com/jamesdsizemore/rush-cliWhat 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 | $0.00766 | $0.00766 |
| Opus 5 | $0.00383 | $0.00383 |
| Sonnet 5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
rush-cli 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 yesterday.
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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rush contributor guide
Project contract
- Python 3.12 package managed with
uv. - Rush is a local CLI and stdio-only MCP server. stdout is JSON-RPC while
rush mcp serveis running; diagnostics and logs belong on stderr. - CLI commands and MCP registrations must call the same implementations in
src/rush/tools/. Do not duplicate tool logic in the transport layer. - Quality engines are discovered from the environment, not bundled as Rush
dependencies. A missing engine returns a structured
skippedresult.
Development
Hermes can expose another Python environment on PATH. Always verify with the project interpreter:
unset VIRTUAL_ENV PYTHONPATH
.venv/Scripts/python.exe -m pytest tests/ -q
.venv/Scripts/ruff.exe check src tests scripts
.venv/Scripts/ruff.exe format --check src tests scripts
Scope and safety
- Keep results in the canonical ToolResult shape: tool, engine/version, status, duration, summary, findings.
- Never write secrets to logs or tool output; redact them as
[REDACTED]. - Workflow tools must never rewrite Git history, install hooks, create tags, publish releases, or upload packages without explicit user-controlled flags.
- Keep
research/local and untracked.
v0.2 configuration
Every [tools.<name>] table in rush.toml must match a canonical TOOL_SPECS
entry. Update the catalog, configuration guide, and example together when
adding a tool.
- Do not commit, publish, or alter release versions unless explicitly asked.
Agent guidelines & anti-patterns
Understanding genuine innovation
- Do not mistake commodity tooling for innovation: Re-labeling existing developer tasks (linters, E2E runners, git commits, database seeders, basic error handling) with buzzwords like "Autonomous" or "Agentic" is not innovation. If an existing Chrome extension, framework, or standard coding assistant already does it, it is not an innovation.
- Do not substitute academic jargon for practical value: Dumping compiler theory (SMT solvers, BDI models, Tarjan SCC algorithms) does not constitute product capability.
- Zero recycling of rejected ideas: Once an idea or direction is rejected, it is permanently blacklisted. Never re-word, re-skin, or re-package it.
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.
- yesterday First seen · 73 lines · 766 tokens per session scan A c837da1b6ce7
rush-cli AGENTS.md is an instructions file published in the GitHub repository jamesdsizemore/rush-cli (0 stars, last pushed 7d ago), licensed MIT. It adds 766 tokens to every session, about $0.0038 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
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.
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).
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.