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/yeaight7/agent-powerups/claude-mdgit clone --depth 1 https://github.com/yeaight7/agent-powerupsWrote 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/yeaight7/agent-powerups/claude-md)<a href="https://agentmods.dev/instructions/yeaight7/agent-powerups/claude-md"><img src="https://agentmods.dev/badge/instructions/yeaight7/agent-powerups/claude-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 | $0.01110 | $0.01110 |
| Opus 5 | $0.00555 | $0.00555 |
| Sonnet 5 | $0.00222 | $0.00222 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
agent-powerups CLAUDE.md 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
npm run build # tsc + postbuild shebang wrapper → dist/
npm test # build then run node test/*.test.ts
Run a single test file:
node --test test/cli.test.ts
No linter is configured. TypeScript strict mode is the primary safety net.
After build, install globally once with npm link. Then the CLI is available as:
apx <command>
Architecture
This repo is an "Oh My Zsh"-style collection of reusable agent powerups (skills, commands, MCP configs, hooks, workflows, templates) for Claude Code, Codex, and Gemini. The APX CLI is the tool users and agents use to browse, validate, check, and install those assets.
catalog.json — single source of truth
Every shipped asset is registered in catalog.json. The Zod schema in src/cli/utils/catalog.ts enforces structure: required fields (name, type, summary, path, compatible_with, maturity), optional fields (requires, targets, mcp, run). Duplicate names are rejected. All referenced paths must exist on disk. When adding a new skill or command, add its catalog entry and verify with apx validate catalog.
Allowed compatible_with values: claude-code, codex, gemini-cli, cursor, generic.
Allowed maturity values: draft, beta, stable.
The targets field holds agent-specific path variants (e.g., .toml for Codex, .json for Claude Code). The requires field declares external dependencies that apx check verifies.
CLI command routing (src/cli/apx.ts)
runCli(argv, io) is the entry point. It finds catalog.json by walking up from cwd, constructs a CatalogService, then dispatches on argv[0] to command modules under src/cli/commands/. Each command exports a run*Command function and returns ExecutionResult<T>. The --json flag switches output to structured JSON for agent consumption.
Asset directories
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 · 75 lines · 1,110 tokens per session scan A 4a85635980f0
agent-powerups CLAUDE.md is an instructions file published in the GitHub repository yeaight7/agent-powerups (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,110 tokens to every session, about $0.0056 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 instructions, from other repositories
agent-skills GEMINI.md
Gemini CLI instructions for mongodb/agent-skills, covering mongodb gemini extension and configuration.
enozunu AGENTS.md
Instructions for tooppoo/enozunu, covering instructions, worktree, pull request, review-sized implementation and skill usage.
mutantx CLAUDE.md
Instructions for Claritune/mutantx, covering mutantx, workflow, project structure, architecture and skills.
akidevrule CLAUDE.md
Instructions for lacvietanh/akidevrule, covering akidevrule, project role, source of truth, file naming conventions and rule authoring principles.
awesome-agent-infrastructure CLAUDE.md
Instructions for backblaze-labs/awesome-agent-infrastructure, covering claude.md — awesome-agent-infrastructure, what this list is, scope and files, schema, workflow, rules.
Skill-HQE AGENTS.md
Instructions for spearchucker667/Skill-HQE, covering agents.md, hqe skill — agent operating instructions, purpose, 1. mission and 2. repository identity.