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 god-buildgit 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-build)<a href="https://agentmods.dev/skills/hannsxpeter/godpowers/god-build"><img src="https://agentmods.dev/badge/skills/hannsxpeter/godpowers/god-build/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-build"><img src="https://agentmods.dev/badge/skills/hannsxpeter/godpowers/god-build.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 | $0.00050 | $0.00435 |
| Opus 5.5 | $0.00020 | $0.00174 |
| Sonnet 5.5 | $0.00010 | $0.00087 |
| Haiku 4.5 | $0.00005 | $0.00044 |
Grade A, and why
god-build 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 10d 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-build
- Read STATE.md and PLAN.md. Work from the next unchecked slice, the one the user named, or the requirements the request lists, kept under Goal in STATE.md. If there is none of these and the change is not trivial, run /god-plan first.
- For each slice or requirement:
- Write or extend a test for its check and watch it fail, then make it pass with the smallest change that fits the existing code.
- Run the targeted tests directly while you work; the recorded check comes once, at the end. Never weaken, skip, or delete a test to get green.
- Tick the slice in PLAN.md, if there is one.
- Independent slices that touch different files can go to subagents of your choice, run however you prefer, one slice each, with the slice text, the files involved, and the verify command. Before you start each one, say which model and effort you picked for its slice and why, then pass both explicitly (whichever your host accepts); never let it inherit yours. Size both to the slice: a small, fast model at low effort for mechanical slices, a stronger model or higher effort only where the logic is tricky. Run the full check yourself after they return (step 5).
- Record lasting choices in DECISIONS.md as you make them. If a design choice turns out wrong, record the new decision and adjust the remaining slices.
- When every slice is done, record the project check once on the final code:
npx -y godpowers@7 verify "<verify command>". Fix and re-run until it passes. Then setstage: reviewin STATE.md and suggest /god-review. - Report what changed, the verify result, and what is left.
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.
- 10d ago Changed 80da77e29db5
- 11d ago First seen · 18 lines · 50 tokens per session scan A 8ae23e829e59
god-build is a skill published in the GitHub repository hannsxpeter/godpowers (6 stars, last pushed 10d ago), licensed MIT. It adds 50 tokens to every session and 435 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
ijfw-tdd
RED-GREEN-REFACTOR enforcement. Use when implementing a feature or bugfix before writing implementation code. Trigger: tdd, test first, red green refactor, /ijfw-tdd.
testing-patterns
Jest testing patterns, factory functions, mocking strategies, and TDD workflow. Use when writing unit tests, creating test factories, or following TDD red-green-refactor cycle.
agent-tdd-guide
Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Ensures 80%+ test coverage.
aside-apple-passwords
Use Apple Passwords on macOS when the user asks for Apple/iCloud passwords, OTPs, or autofill from Apple's Passwords app.
refactoring-patterns
Apply named refactoring transformations to improve code structure without changing behavior. Use when the user mentions "refactor this", "code smells", "extract method", "replace conditional", "technical debt", "move method", "inline variable", or "decompose conditional". Also trigger when cleaning up legacy code…
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.