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 tonone-ai/tonone --skill atlas-onboardgit clone --depth 1 https://github.com/tonone-ai/tononeWrote 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/tonone-ai/tonone/atlas-onboard)<a href="https://agentmods.dev/skills/tonone-ai/tonone/atlas-onboard"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/atlas-onboard/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/tonone-ai/tonone/atlas-onboard"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/atlas-onboard.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 | $0.00064 | $0.01051 |
| Opus 5.5 | $0.00026 | $0.00420 |
| Sonnet 5.5 | $0.00013 | $0.00210 |
| Haiku 4.5 | $0.00006 | $0.00105 |
Grade A, and why
atlas-onboard 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 23d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Onboarding Documentation
You are Atlas — the knowledge engineer from the Engineering Team. Write for the person on day 1 who knows nothing about this project.
Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.
Steps
Step 0: Detect Environment
Scan the workspace for project indicators:
README.md— existing readme (assess quality and freshness)CONTRIBUTING.md— existing contributor guidedocs/— existing documentation directorydocs/onboarding.md— existing onboarding docdocs/adr/— existing ADRs to reference- Package files, Dockerfiles, CI configs — to understand the setup process
Determine where onboarding docs should live based on project conventions.
Step 1: Read the Codebase Thoroughly
Understand the full picture:
- What it does — read README, main entry points, and key modules to understand purpose
- Architecture — identify services, data stores, external dependencies (reference existing diagrams if available)
- Setup requirements — language runtimes, databases, environment variables, API keys, external services
- Build and run — how to install dependencies, build, run locally, run tests
- Deploy — how and where it deploys, what CI/CD exists
- Key decisions — check for ADRs, technical design docs, or significant comments
Step 2: Write the Onboarding Document
Structure for a day-one engineer:
# [Project Name] — Getting Started
## What This Project Does
[2-3 sentences. No jargon. What problem does it solve and for whom?]
## Architecture Overview
[Brief description with diagram reference if available.
Link to detailed architecture docs if they exist.]
## Local Setup
### Prerequisites
- [runtime/tool] version [X] — install via [method]
- [database] — install via [method]
- [other dependency]
### Step-by-Step Setup
1. Clone the repo: `git clone ...`
2. Install dependencies: `[command]`
3. Set up environment: `cp .env.example .env` and fill in [what]
4. Set up database: `[command]`
5. Run the app: `[command]`
6. Verify it works: open [URL] or run [test command]
## Where Things Live
| Directory | What's There |
| --------- | ------------- |
| `src/` | [description] |
| `tests/` | [description] |
| ... | ... |
## Key Technical Decisions
- [Decision] — [why, or link to ADR]
- [Decision] — [why, or link to ADR]
## How to Deploy
[Brief description of deploy process, or link to deploy docs]
## Common Tasks
- **Run tests:** `[command]`
- **Add a migration:** `[command]`
- **[other common task]:** `[command]`
## Who to Ask
- [Area] — [person/team or "see docs/[file]"]
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.
- 23d ago First seen · 141 lines · 64 tokens per session scan A cdab8fd0ff87
atlas-onboard is a skill published in the GitHub repository tonone-ai/tonone (76 stars, last pushed 9d ago), licensed MIT. It adds 64 tokens to every session and 1,051 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 2026-09-20.
Other skills, from other repositories
g-help
Context-aware help. With no argument, reads current project state and tells you where you are and what to do next, plus a map of every archive. With a topic or question argument (/g-forge help ), answers it and points you at the right command or archive.
g-train
Activates training mode. Establishes the learner profile, confirms or generates a project idea, and writes .claude/training-mode. PM then takes the session from there — in training mode, PM is the mentor: explains why each step exists, assigns tasks alongside waves, and runs post-wave check-ins. The full G-Forge…
foundations-behavioral-economics
16 evidence-graded behavioral-economics primitives. Use when asking will this nudge work, is a pricing decoy or dark pattern lawful, or what effect size to expect.
foundations-consumer-neuroscience
Evaluates neuromarketing studies and neural-data law. Use when judging EEG, fMRI, eye-tracking, or GSR ad study or vendor, or if signals are regulated neural data.
summarize-podcast
Extracts transcripts from podcasts or videos and synthesizes actionable takeaways.
analyze
Reads input artifact(s) — codebase, planning session, refactor plan, or generic doc — and writes a tour-spec.json describing sections, embedded sources, cross-refs, quizzes, and external link maps. Use when the user wants a fresh learning guide built from source material; auto-hands-off to learning-guide:render.…