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/quipnetwork/qubitrefill/agents-mdgit clone --depth 1 https://github.com/QuipNetwork/qubitrefillWhat 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 | $0.01501 | $0.01501 |
| Opus 5 | $0.00750 | $0.00750 |
| Sonnet 5 | $0.00300 | $0.00300 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
qubitrefill 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 2d 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.
**Single human stop.** The flow is built to pause in exactly one place — the purchase approval. `mcp__bitrefill__buy-products` is deliberately kept off the `.claude/settings.local.json` allowlist. The six `mcp__qupick__* How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for coding agents working in this repository.
Skills
Bitrefill
qupick's purchase layer is the Bitrefill MCP (https://api.bitrefill.com/mcp) — the mcp__bitrefill__* tools (search-products, product-details, buy-products, get-invoice-by-id). That MCP is the only hard dependency, and nothing from Bitrefill is vendored here. Connect it separately:
claude mcp add --transport http bitrefill https://api.bitrefill.com/mcp --scope user
Optionally, the upstream bitrefill plugin bundles the same MCP plus the bitrefill skill (capability routing, CLI/browse/REST fallbacks, safeguards prose) — /plugin install bitrefill@bitrefill-skills, run inside Claude Code (https://github.com/bitrefill/agents). qupick uses only the MCP tools, not the skill's mechanics.
- Enum/endpoint source of truth: https://docs.bitrefill.com
- Real money: codes deliver instantly and are non-refundable. Confirm product, price, and payment method before buying; use a dedicated low-balance account; never expose high-balance accounts or wallet seeds.
Qupick
Vendored at skills/qupick/SKILL.md. Delegates purchase mechanics to the Bitrefill MCP above and adds portfolio selection on top.
Triggers: "pay with my worst performer", "use my worst crypto to buy X".
Requires: the qupick MCP server — the portfolio backend served at http://127.0.0.1:8000/mcp, exposing mcp__qupick__* tools. The backend must be up when the session starts for the tools to register; if they are missing the skill offers to start it backgrounded with MARKET_DATA_SOURCE = config.backend.marketDataSource (default synthetic) and then has the user reconnect MCP (/mcp). Also a local skills/qupick/config.json (copy of the committed config.example.json; gitignored because it holds the real email), and the agent's API key pasted directly into the .mcp.json Authorization: Bearer header (emailed at registration; Claude Code does not expand ${VAR} in .mcp.json headers, so a literal key is required). Without the config the skill falls back to fully-interactive, on-chain-only behaviour.
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.
- 2d ago First seen · 73 lines · 1,501 tokens per session scan A 379462ec070a
qubitrefill AGENTS.md is an instructions file published in the GitHub repository QuipNetwork/qubitrefill (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,501 tokens to every session, about $0.0075 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 2026-08-31.
Other instructions, from other repositories
divi AGENTS.md
Instructions for QoroQuantum/divi, covering agents.md, dev environment, code style and formatting, testing and documentation.
ln-agent-poc-v2 CLAUDE.md
Instructions for cachet-jp/ln-agent-poc-v2, covering claude.md, project, layout, common commands and architecture notes.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.