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 SyloRei/claude-godmode --skill onboardgit clone --depth 1 https://github.com/SyloRei/claude-godmodeWrote 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/sylorei/claude-godmode/onboard)<a href="https://agentmods.dev/skills/sylorei/claude-godmode/onboard"><img src="https://agentmods.dev/badge/skills/sylorei/claude-godmode/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/sylorei/claude-godmode/onboard"><img src="https://agentmods.dev/badge/skills/sylorei/claude-godmode/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 | $0.00042 | $0.03019 |
| Opus 5 | $0.00021 | $0.01510 |
| Sonnet 5 | $0.00008 | $0.00604 |
| Haiku 4.5 | $0.00004 | $0.00302 |
Grade A, and why
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 9d 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboard
Orient yourself in an unfamiliar codebase fast. Produces a structured cheatsheet — architecture overview, entry points, key conventions, where-things-live, and how-to-run/test — by spawning @researcher for cited findings. Runs read-only: it observes and reports, it never edits.
This is the recommended orientation step for an unfamiliar repo, run before /mission. The cheatsheet sharpens the project charter and roadmap that /mission captures.
Auto Mode
When ## Auto Mode Active is present in context: do not ask clarifying questions. Orient using reasonable defaults (full repo unless a subsystem is named), surface scope assumptions inline, present the cheatsheet, and offer to persist it rather than blocking on it. Treat user course-corrections as normal input.
The Job
Investigate systematically, then present a structured cheatsheet. Spawn @researcher for cited findings and parallel deep dives — never explore the codebase inline when @researcher can do it in parallel.
Process
1. Project Detection (aligns with the Auto-Detection rules in rules/godmode-coding.md)
- Language and framework
- Package manager and build system
- Test runner and coverage setup
- Linter and formatter
- Typechecker
- CI/CD configuration
- Monorepo or single package
- Deployment target (serverless, containers, static)
2. Architecture Map
- Directory structure and organization pattern
- Entry points (main, index, app, handler)
- Key abstractions: core types, interfaces, base classes
- Internal dependency graph
- External dependencies and their roles
3. Convention Analysis
- Naming conventions (files, variables, functions, classes)
- Error handling patterns
- State management approach
- Data flow patterns
- Testing patterns and coverage
4. Code Standards (prescriptive — distinct from Convention Analysis)
Where Convention Analysis above describes the patterns it observes, Code Standards prescribes the DO / DON'T rules the codebase has already established for itself. This step always runs — whether its findings end up persisted is decided later in Saving Results, not here.
What ships with it
1 file 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.
- 9d ago First seen · 259 lines · 42 tokens per session scan A db9f5ddf0fd9
onboard is a skill published in the GitHub repository SyloRei/claude-godmode (3 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 3,019 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
figma-verification
Extract Figma design specs before implementing UI components. Use depth 5, cache to disk, extract ALL properties, map to design system tokens.
interaction-design
Use when designing how a UI feels to use. Covers audience dimensions, discoverability, mode communication, keyboard-first UX, feedback timing, empty states, and information density. Includes WCAG 2.1 AA compliance audit. Companion to visual-design.
browser-testing
Adversarial browser testing. Use when testing UI behavior, verifying network requests, checking console errors, filling forms, or handling dialogs. The goal is finding bugs, not confirming happy paths.
plan-mode
CEO and engineering review after spec-writing. Auto-selects weight class from the spec format (skip for task-mode, eng-only for routine, full CEO+eng for high-risk). Run /spec-writing first.
debugging-protocol
Systematic protocol for diagnosing broken behavior and making recurrence structurally impossible. Schema mismatch causes 80% of bugs. Use when something isn't showing, isn't working, or is still broken after a fix attempt.
figma-extract
Exhaustive Figma node extraction: download every detail down to leaf nodes and cache everything locally. Call Figma once, never twice. Use before any pixel-perfect implementation. Prioritizes complete local dumps over repeated API calls.