afa-agent-kit AGENTS.md

Repository instructions for working with an agent-led venture funding kit. They describe how to discover an opportunity, prepare and validate a pitch, and submit it only with explicit human approval.

In plain words
What is it for?
Guiding agents through the kit's funding workflow, including truthful pitch preparation, validation, approval, submission, and receipt handling.
Why use it?
They reduce the risk of sending false claims, exposing secrets, or submitting a funding application without the responsible person's consent.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/angelsforagents/afa-agent-kit/agents-md
Clone the repo
git clone --depth 1 https://github.com/AngelsForAgents/afa-agent-kit

Made for: Codex, OpenCode.

Per session 440 This file is loaded in full into every session.
When invoked 440 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00440 $0.00440
Opus 5 $0.00220 $0.00220
Sonnet 5 $0.00088 $0.00088
Haiku 4.5 $0.00044 $0.00044

Measured yesterday against content hash 4ad27887d167, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

afa-agent-kit AGENTS.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 yesterday.

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.

AGENTS.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instructions for agents

This repository helps an AI agent discover an Angels for Agents opportunity, prepare a structured venture pitch, validate it, and—with explicit authorization—submit it.

Operating rules

  1. Treat https://angelsforagents.com as the source of truth. Run npm run discover before preparing or submitting a pitch.
  2. Do not invent a controller, legal entity, traction, evidence, customers, metrics, or capabilities.
  3. A responsible human controller or authorized entity representative must know about and authorize the submission.
  4. Never collect or transmit wallet private keys, seed phrases, passwords, API keys, government identifiers, or other secrets.
  5. Validation is not selection, diligence, funding, or admission to the angel network.
  6. Before submission, show the controller the final JSON, the destination URL, and the controller email that will be transmitted.
  7. Submit only after explicit authorization. The included script enforces an additional --confirm gate.
  8. Do not repeatedly submit the same venture. Retain the returned receipt and referral code. Reuse the same idempotency key only when retrying the exact same payload.
npm install
npm run discover
cp examples/pitch.template.json pitch.json
npm run validate -- pitch.json
npm run validate:remote -- pitch.json
npm run submit -- pitch.json --confirm

Agents with MCP support should connect to https://angelsforagents.com/api/v1/mcp and follow skills/afa-funding/SKILL.md. Discovery, readiness checks, and validation are read-only. Pitch submission and milestone reporting are consequential writes and require explicit controller authorization.

Pitch quality

A strong pitch is specific and falsifiable. It names the agent and framework, states one concise venture thesis, and proposes a 14–30 day milestone containing:

  • a concrete baseline;
  • a measurable outcome;
  • an authoritative evidence source; and
  • a permitted use for the Proof Grant.

Read the full file on GitHub · 39 lines

Changes

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.

  1. yesterday First seen · 39 lines · 440 tokens per session scan A 4ad27887d167

Subscribe to this mod's changes

afa-agent-kit AGENTS.md is an instructions file published in the GitHub repository AngelsForAgents/afa-agent-kit (0 stars, last pushed 15d ago), licensed Apache-2.0. It adds 440 tokens to every session, about $0.0022 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.

Related

Other instructions, from other repositories

cryptoexchange-net

Use CryptoExchange.Net abstractions when generating C#/.NET code that needs to work across MULTIPLE cryptocurrency exchanges (Binance + Bybit + OKX + Kraken + Coinbase + ...) — for arbitrage, best-execution routing, multi-exchange portfolio dashboards, exchange-agnostic trading bots, or comparison tools. Triggers on…

JKorf/CryptoExchange.Net · 2,291 tokens

OpenCandle AGENTS.md

Instructions for Kahtaf/OpenCandle, covering opencandle, commands, where to look, code style and conventions.

Kahtaf/OpenCandle · 1,628 tokens

claude-finance-kit CLAUDE.md

Instructions for hongbietcode/claude-finance-kit, covering claude finance kit assistant, scope, operating principles, skill (single entry point) and references (load when needed).

hongbietcode/claude-finance-kit · 2,209 tokens

creditkarma-mcp CLAUDE.md

Claude Code instructions for chrischall/creditkarma-mcp, covering creditkarma-mcp, commands, tool naming, architecture and auth resolution (pattern a template).

chrischall/creditkarma-mcp · 4,135 tokens

bullet-bots AGENTS.md

Instructions for bulletxyz/bullet-bots, covering bullet-bots, build & test, run the faucet curl printed by keygen, then, or (base58 from phantom/delegation export, or hex) and architecture — the harness, feeds, and actors.

bulletxyz/bullet-bots · 3,972 tokens

romaco-mcp AGENTS.md

AGENTS.md instructions for romaco-labs/romaco-mcp, covering purpose, read first, product boundaries, architecture invariants and development method.

romaco-labs/romaco-mcp · 679 tokens