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 agentmods add skills/godshiba/genesis/confignpx skills add godshiba/genesis --skill configgit clone --depth 1 https://github.com/godshiba/genesisWrote 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/config)<a href="https://agentmods.dev/skills/godshiba/genesis/config"><img src="https://agentmods.dev/badge/skills/godshiba/genesis/config.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 | $0.00148 | $0.01928 |
| Opus 5 | $0.00074 | $0.00964 |
| Sonnet 5 | $0.00030 | $0.00386 |
| Haiku 4.5 | $0.00015 | $0.00193 |
Grade B, and why
config 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 5d 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.
- **Global**: `~/.claude/settings.json` — applies everywhere. How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/genesis:config — Configure the gates
GENESIS ships with every gate on. This command changes that without making you
hand-edit JSON or memorize an env var: it reads the current state, walks each
gate, and writes your choice into settings.json under "env". The hooks
re-read the environment when a session starts, so a change lands next session.
The seven gate toggles and their legal values:
| Variable | Values | Gate |
|---|---|---|
GENESIS_G7 |
on / warn / off |
G7 session gate — the only one that blocks |
GENESIS_G1 |
on / warn / off |
G1 unregistered-file nudge |
GENESIS_G3 |
on / warn / off |
G3 orphan TODO/FIXME nudge |
GENESIS_G2_CONFIG |
on / warn / off |
G2 quality-config guard |
GENESIS_G2 |
on / off |
G2 pre-commit validation reminder |
GENESIS_PRECOMPACT |
on / off |
Pre-compaction snapshot |
GENESIS_RESUME |
on / off |
Session-resume loader |
Every one defaults to on; an unset variable is on. warn keeps the
gate's message but never blocks or interrupts (exit 0); off is silent. Only
the first four support warn — the bottom three are on/off. The master
kill switch GENESIS_OFF=1 silences every hook at once; do not offer it in the
walk, but honor it if the user explicitly asks to turn everything off.
Beyond the gates, this command also sets one capability toggle:
GENESIS_GITHUB (on/off, default off) — whether /genesis:issue mirrors
issues to GitHub. It is not a gate (it gates a side-effecting, opt-in
integration), so it is handled on its own in step 3.
1. Read the current state
Two files matter, and a value in the second overrides the first inside that repo:
- Global:
~/.claude/settings.json— applies everywhere. - Per-project:
<repo>/.claude/settings.json— overrides the global value in that repo only.
Read both (either may be missing — treat a missing file or key as the default
on). For each gate compute the effective value: project override, else
global, else default. Print a compact dashboard before asking anything:
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.
- 5d ago First seen · 148 lines · 148 tokens per session scan B 493eb0eaf099
config is a skill published in the GitHub repository godshiba/genesis (2 stars, last pushed 2mo ago), licensed MIT. It adds 148 tokens to every session and 1,928 once invoked, about $0.0007 per session on Opus 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
roadmap-to-workflow
Fan an approved .task/roadmap/ .md out to a dynamic Workflow — parallel planning, serialized implementation, dependency-ordered waves.
to-plan
Capture the chat into .task/task/ .md with ## Description plus ## Plan (Goal/Touches/Logic) — the deepest one-task capture.
self-improve
Self-improve this skills repo — surface and (safely) apply quality improvements across four parallel read-only lenses (Clarity, Leanness, Coverage, Ergonomics). Sibling of /self-audit — audit fixes rule violations, improve raises quality where no rule is broken. Local meta-skill, independent of the /task: pipeline.
to-roadmap
Capture a multi-task initiative into .task/roadmap/ .md — a phase-grouped backlog of ready-to-pick-up items.
to-task
Capture the chat (or a roadmap item) into .task/task/ .md — ## Description only, no ## Plan.
to-spec
Capture load-bearing technical decisions into a standalone .task/spec/ .md — Decision/Rationale/Constrains sections cited via Spec:.