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-onboardinggit 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-onboarding)<a href="https://agentmods.dev/skills/first-tree-ai/first-tree-legacy/first-tree-onboarding"><img src="https://agentmods.dev/badge/skills/first-tree-ai/first-tree-legacy/first-tree-onboarding.svg" alt="Measured on agentmods" 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 | $0.00165 | $0.04223 |
| Opus 5 | $0.00082 | $0.02112 |
| Sonnet 5 | $0.00033 | $0.00845 |
| Haiku 4.5 | $0.00016 | $0.00422 |
Grade C, and why
first-tree-onboarding scanned grade C with 1 finding 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 8d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| `tree verify` fails after Phase B | Print the failures, stop. Most common cause: the sibling tree dir was created but `tree init` was interrupted mid-write. Recovery: `rm -rf <tree_root>` then re-run `tree init`. **Alw How it starts
The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
First Tree Onboarding (one-shot command)
When the user invokes this skill, you (the agent) drive onboarding end to end. Phases A→F below run in order. Within a phase, execute without asking unless the action is irreversible or genuinely ambiguous (see "When to ask the user"). At the end, print the wrap-up summary in Phase F.
Read first: ../first-tree/SKILL.md and ../first-tree/references/structure.md. They define the tree concepts the rest of this skill assumes.
Success criteria (do not claim done until ALL pass)
first-tree tree inspect --json(from the source repo) reportsrole: source-repo-boundorworkspace-root-bound.- The bound tree exists on disk, and
first-tree tree verify --tree-path <tree_root>exits 0. - The tree's
NODE.md,members/owner/NODE.md, and.first-tree/org.yamlcontain real content (no remaining placeholder strings — seereferences/content-drafting.md§Detection). first-tree tree skill doctor --root <source_root>exits 0.- If the user opted in to the daemon:
first-tree github scan doctorexits 0. - The agent has confirmed that Tier 0's
validate.ymlexists, explained that Tier 1 lives infirst-tree-hub, and either skipped Tier 2 or runfirst-tree tree automation install --tier 2 --tree-path <tree_root>and recorded the returned stage. - The user has explicitly confirmed which agent templates to keep in
.first-tree/agent-templates/.
If any of these fails, stop and report — never silently mark onboarding complete.
When to ask the user (default = act)
Ask only before:
- Pushing a branch or PR to a remote (always show diff first).
- Choosing tree mode when both dedicated and shared make sense.
- Recursing into nested repos (
--recursivecascade) when the workspace contains submodules, vendored code, or private sibling repos. - Creating a new GitHub repo for the tree (
gh repo create) — visibility (public/private) must be confirmed. - Deleting partial state to recover from a corrupt binding.
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.
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.
- 8d ago First seen · 234 lines · 165 tokens per session scan C 59340874d559
first-tree-onboarding 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 165 tokens to every session and 4,223 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
brainstorm
Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for wish.
wish
Convert an idea into a structured wish plan with scope, acceptance criteria, and execution groups for work.
dream
Batch-execute SHIP-ready wishes overnight — pick wishes, orchestrate workers, review PRs, wake up to results.
fix
Dispatch fix subagent for FIX-FIRST gaps from review, re-review, then diagnose unresolved failures after 2 loops.