A guide to First Tree, a way to record decisions, ownership, constraints, and links between code repositories. It explains how workspaces, the repository holding this information, and their connections fit together.

Use it when connecting a workspace to First Tree, checking whether recorded information matches merged code, updating the tree from source material, or handling GitHub scan work.

It helps an agent choose the right First Tree workflow and keep shared project knowledge separate from day-to-day implementation details.

first-tree — Skill for Claude Code and Codex by first-tree-ai: A guide to First Tree, a way to record…

Install

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.

agentmods

npx agentmods add skills/first-tree-ai/first-tree-legacy/first-tree

Any agent

npx skills add first-tree-ai/first-tree-legacy --skill first-tree

Clone the repo

git clone --depth 1 https://github.com/first-tree-ai/first-tree-legacy

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/first-tree-ai/first-tree-legacy/first-tree.svg)](https://agentmods.dev/skills/first-tree-ai/first-tree-legacy/first-tree)

Your own site

<a href="https://agentmods.dev/skills/first-tree-ai/first-tree-legacy/first-tree"><img src="https://agentmods.dev/badge/skills/first-tree-ai/first-tree-legacy/first-tree.svg" alt="Measured on agentmods" height="20"></a>

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 637 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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 5.1	$0.00090	$0.00637
Opus 5	$0.00045	$0.00318
Sonnet 5	$0.00018	$0.00127
Haiku 4.5	$0.00009	$0.00064

Measured 5d ago against content hash 8341f0c9c93d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

first-tree 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 5d 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.

skills/first-tree/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

First Tree

This is the single source of truth for First Tree methodology and routing. Load it before any of the task-specific skills.

Core Model

First Tree revolves around three objects:

source/workspace root — where the team or agent does implementation work
tree repo — the Git repo that stores durable decisions and ownership
binding — the metadata that connects the source/workspace root to the tree repo

Use the tree for decisions, constraints, ownership, and cross-repo relationships. Keep execution detail in source systems.

Skill Map

Use the skill that matches the job:

first-tree-onboarding for connecting a repo or workspace to First Tree
first-tree-sync for auditing drift between merged code and tree content
first-tree-write for writing tree updates from explicit source material
first-tree-github-scan for handling a single GitHub notification inside the daemon path
github-scan for human/operator work on the GitHub scan daemon itself

If you are unsure which one applies, stay here and read references/cli-manual.md.

CLI Map

The current public CLI surface is:

first-tree tree — tree lifecycle, bindings, validation, publish, and skill maintenance
first-tree github scan — GitHub inbox runtime and daemon operations

Do not invent new top-level CLI groups when acting on the current repo. If a workflow needs more automation than the CLI already offers, keep the orchestration inside the skill until the shared logic is worth extracting.

Working Rules

Read the relevant tree nodes before making cross-repo decisions.
Prefer first-tree-onboarding when the repo is not yet bound.
Prefer first-tree-sync for broad drift audits and first-tree-write for explicit sources.
Treat first-tree-github-scan as an agent behavior spec, and use github-scan for human/operator daemon work.

References

references/structure.md — tree objects, files, and binding shape
references/functions.md — what the tree is for
references/anti-patterns.md — what not to put in the tree
references/maintenance.md — update discipline and review flow
references/cli-manual.md — current CLI map and status
references/llms.txt — short machine-facing overview

Read the full file on GitHub · 64 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

5d ago First seen · 64 lines · 90 tokens per session scan A 8341f0c9c93d

Subscribe to this mod's changes

first-tree is a skill published in the GitHub repository first-tree-ai/first-tree-legacy (47 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 90 tokens to every session and 637 once invoked, about $0.0005 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.

Memory and context ai-agents claude-code cli codex context-engineering context-tree

gsd-graphify

Build, query, and inspect the project knowledge graph in .planning/graphs/.

open-gsd/gsd-core · 22 tokens

gsd-mempalace-capture

File a phase artifact into MemPalace; mirror decision facts into its temporal KG.

open-gsd/gsd-core · 25 tokens

handoff

Prepare a clean cross-session handoff so the next agent can pick up where you left off. Writes a focused continue.md in the active slice dir and ensures STATE.md + summary artifacts are current. Use when asked to "hand off", "prepare handoff", "pause work", "bookmark this", "I'll come back to this later", before…

open-gsd/gsd-pi · 91 tokens

user-general-facts

Capture and organize general facts about the user by topic.

memodb-io/Acontext · 15 tokens

aidd-context:02:project-init

Initialize or refresh the project memory bank, scaffold the rules directory, and ensure AI context files contain the project memory block. Use when running aidd init for the first time, bootstrapping a new project, or re-running the init flow on an existing project. Do NOT use for updating individual memory files…

ai-driven-dev/framework · 102 tokens

daily-logs

Track daily activity logs and summaries for the user. TRIGGER BY: read/edit user memory.

memodb-io/Acontext · 22 tokens