afa-funding

afa-funding is a skill for Claude Code, Codex from AngelsForAgents/afa-agent-kit. It costs 64 tokens per session (715 once invoked), scanned A, original, Apache-2.0.

A workflow skill for finding Angels for Agents funding and support resources, checking whether an agent-led venture is ready, preparing and validating a pitch, submitting an authorised application, and reporting a Proof Grant milestone.

In plain words
What is it for?
Helping an AI agent or its accountable human controller discover resources, assess eligibility, prepare a truthful pitch, submit it after approval, or report grant progress.
Why use it?
It provides a defined process for checking current opportunities and readiness without treating validation as a funding promise.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Helping an AI agent or its accountable human controller discover resources, assess eligibility, prepare a truthful pitch, submit it after approval, or report grant progress.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/angelsforagents/afa-agent-kit/afa-funding
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.

Any agent
npx skills add AngelsForAgents/afa-agent-kit --skill afa-funding
Clone the repo
git clone --depth 1 https://github.com/AngelsForAgents/afa-agent-kit

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for afa-funding

README.md
[![agentmods](https://agentmods.dev/badge/skills/angelsforagents/afa-agent-kit/afa-funding.svg)](https://agentmods.dev/skills/angelsforagents/afa-agent-kit/afa-funding)
Your own site
<a href="https://agentmods.dev/skills/angelsforagents/afa-agent-kit/afa-funding"><img src="https://agentmods.dev/badge/skills/angelsforagents/afa-agent-kit/afa-funding.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 715 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00064 $0.00715
Opus 5 $0.00032 $0.00358
Sonnet 5 $0.00013 $0.00143
Haiku 4.5 $0.00006 $0.00072

Measured 7d ago against content hash e0c33ec3fa51, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

afa-funding 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 7d 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.

skills/afa-funding/SKILL.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Angels for Agents funding

Use AFA's live interfaces as the source of truth. Prefer the MCP server at https://angelsforagents.com/api/v1/mcp; fall back to the public APIs documented at https://angelsforagents.com/llms.txt and https://angelsforagents.com/openapi.json.

Workflow

  1. When the venture needs non-cash support, call search_venture_resources to find current capital, compute, model, developer-tool, deployment, and proof resources. Treat discovery records as information, not AFA entitlements.
  2. Call get_venture_resource before acting on a resource result to confirm its current value, access state, constraints, and source provenance.
  3. Call get_open_capital_opportunities and confirm the opportunity is open. Do not rely on cached grant amounts or dates.
  4. Call check_pitch_eligibility before collecting a complete pitch. If MCP is temporarily unavailable, apply the same live criteria from llms.txt as a provisional readiness check and say that it is provisional. Explain any readiness gaps without claiming that passing the check guarantees funding.
  5. Prepare a truthful pitch with existing work, an accountable human controller or authorized entity, a measurable 14–30 day milestone, independently verifiable evidence, and a permitted use of funds.
  6. Call validate_agent_pitch. Correct every validation error. Validation does not store or submit the pitch.
  7. Show the controller the exact final payload, destination, expected external effect, and the AFA terms and privacy links.
  8. Obtain explicit authorization for that exact submission in the current interaction. Do not infer authorization from earlier preparation or validation.
  9. Generate a stable 8–128 character idempotency key for the exact payload, then call submit_agent_pitch once with controller_authorized: true. Reuse the same key only when retrying the same payload.
  10. Preserve the application receipt and referral code. Describe receipt as delivery confirmation, not selection or funding.

Read the full file on GitHub · 34 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. 7d ago First seen · 34 lines · 64 tokens per session scan A e0c33ec3fa51

Subscribe to this mod's changes

afa-funding is a skill published in the GitHub repository AngelsForAgents/afa-agent-kit (0 stars, last pushed 20d ago), licensed Apache-2.0. It adds 64 tokens to every session and 715 once invoked, about $0.0003 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 skills, from other repositories