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-hardengit 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-harden)<a href="https://agentmods.dev/skills/hannsxpeter/godpowers/god-harden"><img src="https://agentmods.dev/badge/skills/hannsxpeter/godpowers/god-harden/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-harden"><img src="https://agentmods.dev/badge/skills/hannsxpeter/godpowers/god-harden.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 | $0.00053 | $0.00412 |
| Opus 5.5 | $0.00021 | $0.00165 |
| Sonnet 5.5 | $0.00011 | $0.00082 |
| Haiku 4.5 | $0.00005 | $0.00041 |
Grade A, and why
god-harden 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-harden
- Run the pass yourself, or delegate it to a subagent of your choice, run however you prefer. Either way it covers: the trust boundaries and where untrusted input enters; each OWASP Top 10 (2025) category that can apply to this product form (web app, API, CLI, library, or service), probed against a local build where possible; the dependency audit; committed secrets. A delegated auditor gets the product form, the entry points, and the verify command. Before you start it, say which model and effort you picked and why, then pass both explicitly (whichever your host accepts); never let it inherit yours. Size both to the stakes: the most capable model at high effort for products that handle auth, money, personal data, or internet-facing input; a faster model at lower effort for a small internal tool.
- Findings read
severity: what, where, how to reproduce. Critical means exploitable now (data exposure, auth bypass, code execution). High is exploitable with effort, medium is a defense-in-depth gap, low is hygiene. - Fix criticals and highs now, each with a regression test, then run
npx -y godpowers@7 verify "<verify command>". List anything left open under Risks in STATE.md with its severity. - Record the result on the final code:
npx -y godpowers@7 record harden --pass --summary "<what was checked, counts by severity>". Use--failwhile a critical is open. - When no critical risk is open, set
stage: shipin STATE.md if the user asked to ship, otherwisestage: done.
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 effce377cc82
- 11d ago First seen · 13 lines · 53 tokens per session scan A bb250b468ba8
god-harden is a skill published in the GitHub repository hannsxpeter/godpowers (6 stars, last pushed 10d ago), licensed MIT. It adds 53 tokens to every session and 412 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.
skill-improver
Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existing LLM-first skills.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
ijfw-plan-check
Donahoe Loop audit gate before execution. Trigger: 'audit plan', 'check plan', 'review plan', 'plan audit', 'plan check', 'before we build', 'before execution', 'validate the plan', 'is this plan solid', 'plan review'. Owns pre-execution audit intent -- fires before any foreign plan-checker.
ijfw-cross-audit
Generate a cross-platform multi-model audit (Trident) on a diff, brief, or artifact. Trigger: 'cross audit', 'Trident', 'second opinion', 'check with other models', 'check with other AIs', 'cross-check this', 'get another perspective', /cross-audit.