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/reviewstage/stage-cli/agents-mdgit clone --depth 1 https://github.com/ReviewStage/stage-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 | $0.02665 | $0.02665 |
| Opus 5 | $0.01333 | $0.01333 |
| Sonnet 5 | $0.00533 | $0.00533 |
| Haiku 4.5 | $0.00266 | $0.00266 |
Grade A, and why
stage-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 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to coding agents working in this repository, including Claude Code and Codex.
Build & Development Commands
pnpm install # Install dependencies (also installs husky pre-commit hook)
pnpm dev:web # Start the web UI in Vite dev mode
pnpm build # Build SPA, then bundle the CLI (writes packages/cli/{dist,web-dist})
pnpm test # Run tests (Vitest, from root)
pnpm lint # Biome check (lint + format) — fails on warnings
pnpm lint:fix # Biome check with auto-fix
pnpm format # Format code with Biome
pnpm typecheck # tsc --noEmit across every package (`pnpm -r typecheck`)
The package manager is pinned via packageManager in package.json. Use corepack enable if pnpm isn't on your PATH.
Database (Drizzle ORM + SQLite)
pnpm db:generate # Generate a new migration into packages/cli/drizzle/ from schema changes
The CLI uses an embedded SQLite database via better-sqlite3. There is no separate dev database to start — getDb() opens (or creates) the local SQLite file and runs pending migrations on first use.
Adding UI Components
cd packages/web && npx shadcn@latest add <component>
Components land under packages/web/src/components/ui/ per packages/web/components.json.
Architecture
pnpm workspace. Three packages with real boundaries — no path-alias indirection. The published unit is packages/cli (npm name stagereview, binary stagereview); the rest are private workspace deps that get inlined at build time.
pnpm-workspace.yaml # packages: ["packages/*"]
packages/
cli/ # stagereview — published npm package
src/ # CLI + local HTTP server (Node, ESM)
index.ts # CLI entry (Commander)
show.ts # `stagereview show <path>` implementation
server.ts # Plain Node http server with regex-compiled routes
routes/ # API route handlers (one file per resource)
runs/ # Chapter run import + processing
db/ # Drizzle client, path resolution, schema/
schema.ts # Zod schemas for chapter JSON ingestion (strict)
__tests__/ # Vitest tests
drizzle/ # Generated SQL migrations + meta journal
drizzle.config.ts # Drizzle Kit config
tsdown.config.ts # CLI bundler config (inlines @stagereview/types)
types/ # @stagereview/types (private, TS-native)
src/chapters.ts # Wire-format chapter/key-change schemas + shared HunkReference/LineRef
src/view-state.ts # Wire-format view-state schema
src/index.ts # Barrel re-export
web/ # @stagereview/web (private) — built into ../cli/web-dist
src/components/ # UI components (shadcn/ui under components/ui/)
src/lib/ # Frontend utilities + tests
src/routes/ # SPA route components
src/styles/ # Tailwind globals
vite.config.ts # outDir → ../cli/web-dist
components.json # shadcn config
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 · 189 lines · 2,665 tokens per session scan A 1a1c75201443
stage-cli AGENTS.md is an instructions file published in the GitHub repository ReviewStage/stage-cli (265 stars, last pushed 21d ago), licensed MIT. It adds 2,665 tokens to every session, about $0.0133 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 2026-08-30.
Other instructions, from other repositories
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.