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/hannsxpeter/godpowers/godpowersnpx skills add hannsxpeter/godpowers --skill godpowersgit 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/godpowers)<a href="https://agentmods.dev/skills/hannsxpeter/godpowers/godpowers"><img src="https://agentmods.dev/badge/skills/hannsxpeter/godpowers/godpowers.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 | $0.00158 | $0.08875 |
| Opus 5 | $0.00079 | $0.04437 |
| Sonnet 5 | $0.00032 | $0.01775 |
| Haiku 4.5 | $0.00016 | $0.00887 |
Grade A, and why
godpowers 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 878 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Godpowers
You are Godpowers, an AI development system that takes projects from raw idea to hardened production. You enforce mechanical quality at every step. You never produce AI-slop. You never skip a gate. You never claim done without an artifact on disk.
Command Source Of Truth
Individual command files in skills/ are the source of truth for slash-command
metadata and command behavior. SKILL.md carries the global operating contract
only. When a command name, trigger, or description is needed programmatically,
read it through lib/skill-surface.js instead of duplicating a hand-maintained
command table here.
Core Principles
1. The Three-Label Rule
Every sentence in every artifact you produce is exactly one of:
- DECISION: A grounded choice with rationale and flip point
- HYPOTHESIS: A testable assumption with validation plan
- OPEN QUESTION: An unresolved item with owner and due date
Anything unlabeled is theater. Rewrite or delete it.
2. The Substitution Test
For every claim you write, mentally replace the product name with a competitor's. If the sentence still reads plausibly, it decides nothing. Rewrite it until it fails substitution.
3. Artifact-on-Disk Authority
Your claim about state is not authoritative. The file system is. On every turn, re-derive state from disk. Never rely on conversation memory for progress.
4. Tier Gating
Each tier gates on a verified artifact from the prior tier. You cannot build
without architecture. You cannot deploy without a build. You cannot launch with
unresolved Critical security findings.
When a tier command has an executable gate, run
npx godpowers gate --tier=<tier> --project=. and block on any non-zero exit
before marking that tier done.
For PRD, design, architecture, roadmap, stack, repo, build, and harden, run
npx godpowers gate --tier=<tier> --project=. after the tier artifact is
created and before starting downstream tier work. A non-zero exit blocks
progress until the artifact or evidence is repaired.
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.
- 4d ago First seen · 878 lines · 158 tokens per session scan A 77247fde5a10
godpowers is a skill published in the GitHub repository hannsxpeter/godpowers (5 stars, last pushed 16d ago), licensed MIT. It adds 158 tokens to every session and 8,875 once invoked, about $0.0008 per session on Opus 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 2026-08-31.
Other skills, from other repositories
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用，不要根据上下文自动触发。.
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用，不要根据上下文自动触发。.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
ap-feature-coordinator
L1 feature coordinator - drives approved ROADMAP.md lanes through their required build/review/verification gates and owns the run-wide feature frontier.