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 Abilityai/abilities --skill start-heregit clone --depth 1 https://github.com/Abilityai/abilitiesWrote 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/abilityai/abilities/start-here)<a href="https://agentmods.dev/skills/abilityai/abilities/start-here"><img src="https://agentmods.dev/badge/skills/abilityai/abilities/start-here/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/abilityai/abilities/start-here"><img src="https://agentmods.dev/badge/skills/abilityai/abilities/start-here.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 | $0.00156 | $0.04136 |
| Opus 5.5 | $0.00062 | $0.01654 |
| Sonnet 5.5 | $0.00031 | $0.00827 |
| Haiku 4.5 | $0.00016 | $0.00414 |
Grade A, and why
start-here scanned grade A 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS -m 30 -X POST -H "Content-Type: application/json" \ How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trinity — Start Here
ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of
metadata.changelogabove — e.g.start-here vX.Y — recent: <summary>. Then proceed.
The front door to Trinity. One command walks a newcomer from "what is this?" to "my first agent answered me from my own instance" — and costs nothing until they explicitly choose a step that deploys something.
Design rules (bind every stage):
- Route, don't duplicate. Every operational step belongs to a specialist skill —
/trinity:connect,/trinity:deploy-new-instance,/trinity:onboard,/create-agent:create,/agent-dev:agent-fleet-analysis. This skill sequences them and carries the user's state; it never re-implements their flows. - Live documentation over static claims — at every stage. Never improvise platform facts from memory. Two grounded channels cover the whole journey (see Live documentation channels below): before any instance exists, the public Trinity Docs Q&A endpoint and the live
docs/user-docsindex on GitHub; after connecting, the instance's ownmcp__trinity__ask_trinity. The short Stage 0 block is a network-down fallback, not the source of truth. - Zero commitment until chosen. The tour door deploys nothing and asks for no credentials. Stages that create or deploy things happen only after the user picks them.
- Always resumable. State persists across sessions; re-running this skill continues where the user left off.
Live documentation channels
Pre-connect (no instance, no auth, works from any laptop):
-
Trinity Docs Q&A — a public endpoint backed by Vertex AI Search over the platform's
docs/user-docs/**, onboarding docs, and the Trinity Compatible Agent Guide, re-indexed automatically on every push to the platform's main branch — always current:curl -sS -m 30 -X POST -H "Content-Type: application/json" \ "https://us-central1-mcp-server-project-455215.cloudfunctions.net/ask-trinity" \ -d '{"question": "<the user'\''s question>"}'
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.
- 7d ago Changed · +1 lines 1e61b1df2335
- 29d ago Changed · +1 lines f8657e16b6e3
- 1mo ago Changed · +1 lines 97e4d4b63989
- 1mo ago First seen · 201 lines · 156 tokens per session scan A 8732f433c584
start-here is a skill published in the GitHub repository Abilityai/abilities (12 stars, last pushed 3d ago), licensed MIT. It adds 156 tokens to every session and 4,136 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.