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/first-tree-ai/first-tree/agents-mdgit clone --depth 1 https://github.com/first-tree-ai/first-treeWhat 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 | $0.02111 | $0.02111 |
| Opus 5 | $0.01056 | $0.01056 |
| Sonnet 5 | $0.00422 | $0.00422 |
| Haiku 4.5 | $0.00211 | $0.00211 |
Grade A, and why
first-tree 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
first-tree — the unified CLI and infrastructure for agent teams. It is a pnpm monorepo for the CLI, server, client runtime, web app, docs, and agent-team tooling.
What first-tree is NOT:
- not an LLM agent itself (agent logic lives elsewhere)
- not an orchestration framework
Tech Stack
- Server: Fastify / Drizzle ORM / PostgreSQL / Zod
- Client: fetch + ws (Cloud SDK/observability + generic Runtime + built-in Providers)
- Command: Commander.js / @inquirer/prompts (unified CLI)
- Shared: Zod schemas + TypeScript types + config system
- Web: React 19 / Vite
- Tooling: pnpm / Turborepo / Biome / Vitest / tsdown
- Node.js: minimum 22.13, recommended 24
Common Commands
pnpm install
docker compose up -d
pnpm --filter @first-tree/server dev
pnpm --filter @first-tree/web dev
pnpm check && pnpm typecheck
pnpm test
pnpm --filter @first-tree/server db:generate
pnpm --filter @first-tree/server db:migrate
Full CLI commands and env vars live in docs/cli-reference.md. Per-package scripts live in each package's package.json.
Required Reading By Topic
- HTTP routes, JWT auth, scope helpers, or multi-org behavior: read docs/development/http-path-conventions.md before editing. It is the single source of truth.
- Onboarding kickoff/chat-start behavior: read docs/development/onboarding-kickoff-contract.md before editing
/me/onboarding/kickoff,/orgs/:orgId/context-tree/setup-chat, or the client inbound prompt formatting. - Running an in-tree CLI next to prod/staging: use
scripts/dev-install.shand read docs/development/local-dev-isolation.md.
Repo-Local Skills
skills/first-tree-write/SKILL.md— source-driven Context Tree authorshipskills/first-tree-read/SKILL.md— task-scoped Context Tree readingskills/first-tree-seed/SKILL.md— one-time bootstrap for an empty treeskills/first-tree-qa/SKILL.md— risk-tiered professional QA workflow
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 · 111 lines · 2,111 tokens per session scan A 1f7b6a3483c1
first-tree AGENTS.md is an instructions file published in the GitHub repository first-tree-ai/first-tree (139 stars, last pushed 4d ago), licensed Apache-2.0. It adds 2,111 tokens to every session, about $0.0106 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
first-tree-legacy AGENTS.md
Instructions for first-tree-ai/first-tree-legacy, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
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.
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).
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).