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 skills add first-tree-ai/first-tree-legacy --skill first-tree-writegit clone --depth 1 https://github.com/first-tree-ai/first-tree-legacyWrote 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.
[](https://agentmods.dev/skills/first-tree-ai/first-tree-legacy/first-tree-write)<a href="https://agentmods.dev/skills/first-tree-ai/first-tree-legacy/first-tree-write"><img src="https://agentmods.dev/badge/skills/first-tree-ai/first-tree-legacy/first-tree-write/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/first-tree-ai/first-tree-legacy/first-tree-write"><img src="https://agentmods.dev/badge/skills/first-tree-ai/first-tree-legacy/first-tree-write.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00073 | $0.00946 |
| Opus 5.5 | $0.00029 | $0.00378 |
| Sonnet 5.5 | $0.00015 | $0.00189 |
| Haiku 4.5 | $0.00007 | $0.00095 |
Grade A, and why
first-tree-write 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 1mo 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
First Tree Write
Read these first:
../first-tree/SKILL.md../first-tree/references/anti-patterns.md../first-tree/references/maintenance.md
What This Skill Does
Take one specific source — a PR, a doc, a note — and produce zero, one, or a small set of tree changes that capture what's durable and decision- relevant. The output is a tree-repo PR linked to the source.
When To Use This Skill
| Use this skill | Use a different skill |
|---|---|
| User pastes a PR link and says "reflect this in the tree" | User asks "is the tree up to date?" → first-tree-sync |
| User pastes a meeting note about a decision | Repo is unbound → first-tree-onboarding first |
| User pastes raw text and asks for the tree implication | A GitHub notification needs only a label / comment → first-tree-github-scan |
GitHub Scan agent classifies a notification as route=write |
Audit drift since a release → first-tree-sync |
The Default Stance
Default to not writing. The tree compresses expensive context; a node nobody reads is worse than a missing node. If the source does not clearly establish a decision, constraint, ownership change, or cross-domain relationship, write nothing and tell the user why.
How To Run
| Phase | Reference |
|---|---|
| Decide what is tree-worthy | references/what-belongs.md |
| Draft the update | references/workflow.md |
| Shape the tree node | references/node-shape.md |
| Decide between write and sync | references/boundary.md |
What ships with it
6 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.
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.
- 1mo ago First seen · 86 lines · 73 tokens per session scan A a0a25d914431
first-tree-write is a skill published in the GitHub repository first-tree-ai/first-tree-legacy (47 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 73 tokens to every session and 946 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
learn
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.
brief
Brief the user on what they saved in a period — the thread running through it, not a list.
resurface
Pick a few old saves worth revisiting now, and say why now.
first-tree-seed
Bootstrap a team's Context Tree from readable source repos — for an onboarding "build / set up the Context Tree" task on a tree that has no domain structure yet: either no tree exists (creates and binds it) or a bound-but-empty tree (fills it). Supports clean explicit-Team invocation without a Workspace manifest…
first-tree-write
Source-driven Context Tree write workflow for managed and BYO consumers. BYO always requires the exact SCOPE-routed read snapshot and a new user confirmation of the precise Team/source/targets/mutation plan before any Tree mutation. If no source artifact is available, there is no write task.
meeting-to-tree
Turn exact meeting records that the user supplies into durable Context Tree updates. Use when a user asks to sync meeting minutes, transcripts, AI notes, decision records, or related meeting artifacts into the team's Context Tree: read the exact sources, reconcile chronology, identify durable decisions and…