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 commands/wingedguardian/genesis-agi/setupgit clone --depth 1 https://github.com/WingedGuardian/GENesis-AGIWhat 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 | $0.00061 | $0.00844 |
| Opus 5 | $0.00030 | $0.00422 |
| Sonnet 5 | $0.00012 | $0.00169 |
| Haiku 4.5 | $0.00006 | $0.00084 |
Grade B, and why
setup scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
python scripts/setup_claude_config.py --global # also update ~/.claude/settings.json How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Genesis Setup
/setup covers two jobs — finishing/repairing the install and running
first-run onboarding — and routes between them from the system's actual
state. Detect first, then route; do not assume.
Step 1 — Detect state
Two independent signals:
-
Infrastructure — did the Layer-1 install (
bootstrap.sh/install.sh) actually finish? An interrupted install leaves the venv or dependencies incomplete, and the~/.genesis/setup-completemarker absent (it is written only at the very end). Check that the venv exists and the package imports:ROOT="$(git rev-parse --show-toplevel 2>/dev/null || pwd)" "$ROOT/.venv/bin/python" -c "import genesis" 2>/dev/null && echo INFRA_OK || echo INFRA_INCOMPLETE -
Onboarding — has the system been configured? The marker is written at the end of onboarding (or by a completed
bootstrap.sh):test -f ~/.genesis/setup-complete && echo ONBOARDED || echo NOT_ONBOARDED
Step 2 — Route (decide in this order)
- INFRA_INCOMPLETE — the install is broken or half-finished (e.g. an
interrupted
bootstrap.sh). Onboarding cannot run on a broken install, so repair the infrastructure first → Config repair below. After it completes, if keys/identity still need configuring, ask Genesis to "run onboarding" — the skill will run the sections you need. - INFRA_OK + NOT_ONBOARDED — a complete install that has not been configured → Guided onboarding below. (Even if the user said "repair" — there is no configured system to repair yet; onboarding is the setup.)
- INFRA_OK + ONBOARDED — an already-configured install → Config repair
below (the usual reason to run
/setupon a working system).
Guided onboarding
Read src/genesis/skills/onboarding/SKILL.md and follow its steps: it configures
the user profile, essential API keys, Telegram, GitHub backup, and verifies
endpoints, then writes the ~/.genesis/setup-complete marker itself at the end.
Do not run bootstrap.sh for onboarding — bootstrap is infrastructure setup,
not the onboarding flow.
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.
- 3d ago First seen · 80 lines · 61 tokens per session scan B 492276c937ec
setup is a command published in the GitHub repository WingedGuardian/GENesis-AGI (93 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 844 once invoked, about $0.0003 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 2026-08-30.
Other commands, from other repositories
phase-status
Report progress against the current phase in docs/phases.md.
add-adr
Create a new numbered Architecture Decision Record.
daily-log
Append entry to today's daily log.
review-prs
Check open PRs for human feedback before picking new work.
brief-refresh
Audit docs for staleness and contradictions, propose new features.
new-module
Scaffold a new module that registers with core.