Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add godshiba/genesis/plugin install genesis-usageWrote 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/godshiba/genesis/setup)<a href="https://agentmods.dev/skills/godshiba/genesis/setup"><img src="https://agentmods.dev/badge/skills/godshiba/genesis/setup/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/godshiba/genesis/setup"><img src="https://agentmods.dev/badge/skills/godshiba/genesis/setup.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 | $0.00081 | $0.01848 |
| Opus 5.5 | $0.00032 | $0.00739 |
| Sonnet 5.5 | $0.00016 | $0.00370 |
| Haiku 4.5 | $0.00008 | $0.00185 |
Grade B, and why
setup scanned grade B 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 1mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.claude/settings.json` so you never hand-edit JSON or memorize an env var. 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.
/genesis-usage:setup - Configure the usage sensor
The sensor works out of the box; this makes it yours. It writes choices into
~/.claude/settings.json so you never hand-edit JSON or memorize an env var.
If the user passed a number as an argument (e.g. /genesis-usage:setup 80),
treat it as the 5-hour cap - but still show the weekly cap (default 85) so it is
never set silently. A second number sets the weekly cap too
(/genesis-usage:setup 80 75).
1. Check eligibility first (be honest)
The sensor only fires on Claude.ai Pro/Max (Claude Code v1.0.80+), and
only after the first model response in a session - that is when Claude Code
starts sending rate_limits. On API-key-only accounts it stays silent by
design. If the user is on API keys, say so plainly and stop - configuring it
will not make data appear.
Critical: rate_limits is delivered to the statusline input only, never
to hook input. The sensor is a Stop hook, so it gets its data from a bridge file
the statusline writes each render. The statusline is therefore required, not
optional - without it the sensor has no usage data and never fires. Treat
step 4 as part of the core setup, not an extra.
2. Ask what they want (one short round)
Show every setting's current value (or its default) and let the user keep or change it - never leave a setting at a default the user never saw. Both caps are first-class; present them as a pair:
- 5-hour cap - usage %% that triggers the warning (default 90).
- 7-day (weekly) cap - usage %% that triggers the weekly warning (default 85).
- Mid-turn watch -
on/off(default off). Ask this right after the two caps, because it builds on them. Describe it plainly: the normal sensor only checks at the end of each turn, so a single large multi-tool turn can blow past the cap before it ever fires. Turning this on adds a PostToolUse hook that checks the same usage numbers after every tool call, so a crossing is caught between tools - inadviseit warns you and Claude mid-turn; inenforce(inside a GENESIS project) it writes a snapshot itself and tells Claude to run/genesis:closebefore the next tool. Default off because it runs on a hot path; suggestonto anyone who runs long agentic turns. It reuses the same caps and the once-per-bucket throttle, so it adds no new tuning. - Mode -
advise(warn in the terminal, default),enforce(block the turn so Claude runs/genesis:close), oroff. Note: mid-turn watch follows this same mode. - Desktop notification -
on/off(default off). When on, the sensor also posts a macOS notification, useful when you are working in another app. - Statusline - required data feed (see step 4). Default to installing it; only skip if the user already runs a statusline they will not replace - and warn them the sensor cannot fire without one.
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.
- 1mo ago First seen · 141 lines · 81 tokens per session scan B 352883b7abb7
setup is a skill published in the GitHub repository godshiba/genesis (2 stars, last pushed 4mo ago), licensed MIT. It adds 81 tokens to every session and 1,848 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
genius-file
Read and update Working Genius work files — the work's folder holding the bounded snapshot a cold session acts on, the append-only log behind it, and the contract that binds the unbuilt slices. Use when a stage skill needs the work-file discipline, when the user asks what work is in flight or where a piece of work…
weekly-metrics
Generate a weekly productivity metrics report for solo AI-assisted development. Analyzes git commits, TaskNotes, and collaboration patterns from the last 7 days, then proposes workflow optimizations. Use this skill whenever the user asks for a weekly report, productivity metrics, sprint retrospective, workflow…
claude-autopilot
A time-limited autonomous agent for Claude Code that follows a user directive until a specified deadline. It breaks work into tasks, tracks progress, and winds down before time runs out.
excalidraw
Create Excalidraw diagrams programmatically. Use when the user wants architecture diagrams, flowcharts, or any visual diagram with a hand-drawn aesthetic, where editable output and drag-and-drop editing add value over Mermaid's text-only approach.
ia
Evaluate and improve how information is organized for findability. Use when the user asks to "organize this", "restructure docs", "improve navigation", "where should this go", "review file structure", or when documentation grows beyond a single page.
naming
Evaluate and improve names in code using naming as a design diagnostic. Use when the user asks to "name this", "rename", "review naming", "what should I call", struggles to name something, or when a code review surfaces vague or misleading names.