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 instructions/pivyme/suiperpower/agents-mdgit clone --depth 1 https://github.com/pivyme/suiperpowerWrote 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/instructions/pivyme/suiperpower/agents-md)<a href="https://agentmods.dev/instructions/pivyme/suiperpower/agents-md"><img src="https://agentmods.dev/badge/instructions/pivyme/suiperpower/agents-md.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 | $0.01728 | $0.01728 |
| Opus 5 | $0.00864 | $0.00864 |
| Sonnet 5 | $0.00346 | $0.00346 |
| Haiku 4.5 | $0.00173 | $0.00173 |
Grade A, and why
suiperpower AGENTS.md scanned grade A 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Suiperpower is the open platform behind https://suiperpower.dev. Skills, knowledge, ecosystem catalog, and a CLI for shipping production Sui products. Distributed via curl one-liner. Built around an explicit anti-slop qu How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md, Suiperpower
Context for any AI coding agent (Codex, Cursor, generic LLM tools) working on the Suiperpower codebase itself. Mirrors CLAUDE.md. If you are running as Claude Code, read CLAUDE.md; everything else, read this file.
What this project is
Suiperpower is the open platform behind https://suiperpower.dev. Skills, knowledge, ecosystem catalog, and a CLI for shipping production Sui products. Distributed via curl one-liner. Built around an explicit anti-slop quality bar so projects survive past hackathons, not just win them.
Tagline: Build something meaningful, on Sui
The launch occasion is Sui Overflow 2026, but Suiperpower is a long-lived production tool, not a hackathon helper.
Tech stack
- Language: TypeScript (strict, ESM, NodeNext)
- Runtime: Node.js 20+
- Package manager: pnpm workspaces
- CLI: zero runtime deps. The Convex backend owns its own package dependencies.
- Backend: Convex (telemetry + feedback only)
- Website: static setup assets today, full site is separate from the core CLI work
- Skills: plain markdown (Anthropic skill spec) with optional
references/andagents/openai.yaml. Grok Build reads this same Anthropic format straight from~/.grok/skills/, so no Grok-specific generator exists - Knowledge base: plain markdown
- Ecosystem catalog: plain JSON
- Install: bash script hosted at suiperpower.dev/setup.sh, npm package
@pivyme/suiperpower
Project structure
On-disk shape today:
suiperpower/
├── README.md, CLAUDE.md, AGENTS.md, CONTRIBUTING.md, LICENSE
├── package.json, pnpm-workspace.yaml
├── core/ publishable npm package "@pivyme/suiperpower"
│ ├── cli/ CLI source + cli/data/ ecosystem catalog
│ ├── skills/ SKILL_ROUTER.md + per-phase skill folders + skills/data/
│ ├── scripts/ release tooling (preamble injector, lint, package)
│ ├── install.sh curl one-liner bootstrap
│ └── skills-lock.json
├── convex/ telemetry + feedback backend
└── web/ static setup assets + website shell
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.
- 5d ago First seen · 120 lines · 1,728 tokens per session scan A 6c9a40b79cfb
suiperpower AGENTS.md is an instructions file published in the GitHub repository pivyme/suiperpower (12 stars, last pushed 25d ago), licensed MIT. It adds 1,728 tokens to every session, about $0.0086 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
SeekMoney-ai CLAUDE.md
Claude Code instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.
critical-thinking AGENTS.md
Instructions for Johna2an/critical-thinking, covering agents.md, repo map, install (for a user asking "should i install this?"), working in this repo and running an eval round.
idd-skill idd-resume.instructions.md
Instructions for kurone-kito/idd-skill, covering idd — resume phase, required inputs, step 0 — route classifier, operator-present release and step 1 — identify claim state.
hometax-doum AGENTS.md
AGENTS.md instructions for lbiz-partners/hometax-doum, covering claude.md — hometax-doum 개발 규칙 (하네스와 쌍), 규칙 ↔ 강제 장치 and 운용 메모.
powerglide AGENTS.md
Instructions for bkataru/powerglide, covering powerglide agent protocol & integration guide, the ralph loop protocol, termination signals, velocity control and reliable pty execution.
Copilot-Skills langchain.instructions.md
Instructions for TheSethRose/Copilot-Skills, covering langchain instructions, default behaviors, common workflows, basic chain setup and with claude.