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 hannsxpeter/godpowers --skill godgit clone --depth 1 https://github.com/hannsxpeter/godpowersWrote 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/hannsxpeter/godpowers/god)<a href="https://agentmods.dev/skills/hannsxpeter/godpowers/god"><img src="https://agentmods.dev/badge/skills/hannsxpeter/godpowers/god/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/hannsxpeter/godpowers/god"><img src="https://agentmods.dev/badge/skills/hannsxpeter/godpowers/god.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 | $0.00047 | $0.00448 |
| Opus 5.5 | $0.00019 | $0.00179 |
| Sonnet 5.5 | $0.00009 | $0.00090 |
| Haiku 4.5 | $0.00005 | $0.00045 |
Grade A, and why
god 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 11d 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.
What it actually says
/god
- Run
npx -y godpowers@7 status. If there is no project, offer /god-init (it also migrates 6.x projects) and stop. - With no goal: answer in at most five lines: where the project stands, the single next step, and the command for it.
- With a goal, pick the smallest path that does it well, skipping any stage STATE.md shows is already done for this goal:
- A question or assessment: answer from the code and the state files.
- A small change (one slice, low risk, no trust boundary): make it, run
npx -y godpowers@7 verify "<verify command>", and touch STATE.md only if the stage or risks changed. - A feature: /god-plan, /god-build, then /god-review. When the request already lists its requirements, skip /god-plan: write the goal and those requirements, one line each, under Goal in STATE.md, set
stage: build, and build from them. Add /god-harden only when the change touches a trust boundary: auth, secrets, untrusted input, money, or deleting data. - A new product, or a large or unclear goal: /god-plan in full, /god-build, /god-review, and /god-harden.
- Run /god-ship only when the user asks to ship, release, or deploy. Its gate needs a security record for the current code, so run /god-harden first if there is none.
- Keep going between the stages you chose without asking. Stop only for decisions that belong to the user (scope, spending, credentials, public or irreversible actions), or when the same gate fails twice for the same reason.
- Finish with what changed, the verify result, open risks, and the next step.
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.
- 11d ago First seen · 19 lines · 47 tokens per session scan A 04cc2bf90b20
god is a skill published in the GitHub repository hannsxpeter/godpowers (6 stars, last pushed 10d ago), licensed MIT. It adds 47 tokens to every session and 448 once invoked, about $0.0002 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 2026-09-27.
Other skills, from other repositories
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
ijfw-workflow
Use when the user says: 'build', 'create', 'plan', 'new project', 'brainstorm', 'design', 'UI', 'website', 'dashboard', 'app', 'help me build', 'launch', 'book', 'campaign', or anything project-level. Skill body decides Quick vs Deep path.
ijfw-plan
Use when the user says 'plan this', 'plan it', 'make a plan', 'let's plan', 'draft a plan', 'how should we tackle this', 'break this down', or invokes '/ijfw-plan'. Produces a falsifiable PLAN.md (software, book, campaign, design, research) with task breakdown, dependency wave-table, and success criteria — gated by…
ijfw-ship
Use when the user says 'ship it', 'ship this', 'release', 'publish', 'launch', 'deploy', 'go live', 'wrap this up', 'time to ship', or invokes '/ijfw-ship'. Domain-aware release — software (test → tag → push → publish), book (final edit → format → KDP / agent / Substack), campaign (review → schedule → launch →…
ijfw-complete-milestone
Use when a milestone is shipping and you need to archive its artifacts, generate a summary, and seed the next milestone. Trigger: 'milestone complete', 'ship milestone', 'wrap milestone', 'complete milestone ', /ijfw-complete-milestone.