first-tree-github-scan

first-tree-github-scan is a skill for Claude Code, Codex from first-tree-ai/first-tree-legacy. It costs 113 tokens per session (1,093 once invoked), scanned A, original, Apache-2.0.

A skill used by an automated First Tree process to handle one GitHub notification at a time. It classifies events such as pull requests, issues, review requests, mentions, and CI results, then chooses a response or handoff route.

In plain words
What is it for?
Use it in the First Tree GitHub-scan workflow to label notifications, post appropriate comments, route work, and emit the result needed by the automation.
Why use it?
It gives incoming GitHub events a consistent decision process. This helps determine whether an event needs a reply, human attention, synchronization, or a content change.

Skill for Claude CodeCodex

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-github-scan
Any agent
npx skills add first-tree-ai/first-tree-legacy --skill first-tree-github-scan
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.

agentmods badge for first-tree-github-scan

README.md
[![agentmods](https://agentmods.dev/badge/skills/first-tree-ai/first-tree-legacy/first-tree-github-scan.svg)](https://agentmods.dev/skills/first-tree-ai/first-tree-legacy/first-tree-github-scan)
Your own site
<a href="https://agentmods.dev/skills/first-tree-ai/first-tree-legacy/first-tree-github-scan"><img src="https://agentmods.dev/badge/skills/first-tree-ai/first-tree-legacy/first-tree-github-scan.svg" alt="Measured on agentmods" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,093 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.

ModelPer sessionOnce invoked
Fable 5 $0.00113 $0.01093
Opus 5 $0.00056 $0.00547
Sonnet 5 $0.00023 $0.00219
Haiku 4.5 $0.00011 $0.00109

Measured 3d ago against content hash f8282f3e836b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

first-tree-github-scan 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 3d 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-github-scan/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

First Tree Github Scan

Read these first:

  • ../first-tree/SKILL.md
  • ../first-tree/references/functions.md
  • ../first-tree/references/anti-patterns.md

What This Skill Does

This skill is loaded by the daemon every time a new GitHub notification arrives and a per-task agent is spawned. The agent's job is to:

  1. classify the notification
  2. set the right github-scan:* label and post any necessary comment
  3. choose exactly one of four routes (reply / human / sync / write)
  4. emit a GITHUB_SCAN_RESULT: line so the daemon can dispatch downstream work

This is not the operator-facing daemon guide. Humans running first-tree github scan install / start / doctor should use the CLI help, not this skill.

When To Use This Skill

Use this skill Use a different skill
The daemon spawned an agent for one notification A user wants to onboard a repo → first-tree-onboarding
You need the tag table or comment template A user wants to audit drift → first-tree-sync
You need the route taxonomy A user wants to write tree content from a source → first-tree-write
You need to decide whether to involve a human An operator is debugging the daemon — use first-tree github scan --help

The Four Tags

github-scan:new      — initial state; daemon also restores via auto-revert
github-scan:wip      — agent has started real work
github-scan:human    — a human must step in
github-scan:done     — finished, no further action

Exactly one github-scan:* label per item at any time. Full lifecycle and gh calls in references/tags.md.

The Four Routes

reply  — handle on GitHub: labels / review / comments
human  — set github-scan:human and stop
sync   — load first-tree-sync SKILL.md and continue under that skill
write  — load first-tree-write SKILL.md and continue under that skill

Read the full file on GitHub · 103 lines

Files

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.

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.

  1. 3d ago First seen · 103 lines · 113 tokens per session scan A f8282f3e836b

Subscribe to this mod's changes

first-tree-github-scan 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 113 tokens to every session and 1,093 once invoked, about $0.0006 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.