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/fetchai/agentverse-skills/agents-mdgit clone --depth 1 https://github.com/fetchai/agentverse-skillsWrote 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/fetchai/agentverse-skills/agents-md)<a href="https://agentmods.dev/instructions/fetchai/agentverse-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/fetchai/agentverse-skills/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 | $0.00727 | $0.00727 |
| Opus 5 | $0.00364 | $0.00364 |
| Sonnet 5 | $0.00145 | $0.00145 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade B, and why
agentverse-skills AGENTS.md scanned grade B with 2 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 3d 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
- **Helpful errors**: If env var missing, print instructions on how to get one Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Read Bash(python3 *) Bash(curl *) Bash(pip install requests) How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions for AI Agents Working on This Repo
What This Repo Is
This is a collection of portable agent skills (SKILL.md format) that enable AI coding agents to interact with Fetch.ai's Agentverse platform programmatically.
Repo Structure
skills/— Each subdirectory is a self-contained skillSKILL.md— The skill definition (what you read to learn the skill)scripts/— Runnable Python scripts (only dependency:requests)references/— Deep documentation and protocol details
examples/— Worked examples showing real outputsdocs/— Reference documentation (API, auth, troubleshooting)
How to Add a New Skill
- Create
skills/<skill-name>/SKILL.mdwith proper frontmatter - Create
skills/<skill-name>/scripts/<script>.py— self-contained, CLI-ready - Add entry to the table in
README.md - Add a worked example in
examples/if non-trivial
Skill Script Requirements
- Self-contained: Only needs
requestslibrary (stdlib + requests) - CLI interface: Uses
argparse, runnable from command line - JSON output: Results go to stdout as valid JSON
- Error handling: Logs/errors go to stderr, exit code 1 on failure
- Env vars: Uses
AGENTVERSE_API_KEY(orASI_ONE_API_KEYfor ASI:One) - Helpful errors: If env var missing, print instructions on how to get one
- Apache 2.0 license header
SKILL.md Format
Follow the SKILL.md specification:
---
name: skill-name
description: >
One-paragraph description of what this skill does.
Include trigger phrases and key capabilities.
license: Apache-2.0
compatibility: Python 3.8+, network access, AGENTVERSE_API_KEY env var
metadata:
version: "1.0.0"
author: "Fetch.ai"
last-updated: "2026-04-20"
allowed-tools: Read Bash(python3 *) Bash(curl *) Bash(pip install requests)
---
Key Technical Facts
- Base URL:
https://agentverse.ai - Auth:
Authorization: Bearer {AGENTVERSE_API_KEY} - Working API version: V1 (
/v1/hosting/agents,/v1/almanac/...) - Code upload format:
{"code": json.dumps([{"language":"python","name":"agent.py","value":"..."}])} - Hosted env:
agentis pre-created — do NOT useAgent()or.run() - Logs are output: Use
ctx.logger.info()— no stdout/stderr in hosted env - Image gen timing: ACK ~1s, text response ~3s, image response ~30s
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.
- 3d ago First seen · 72 lines · 727 tokens per session scan B 333c5ae4be49
agentverse-skills AGENTS.md is an instructions file published in the GitHub repository fetchai/agentverse-skills (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 727 tokens to every session, about $0.0036 per session on Opus 5. A static security scan graded it B with 2 findings (asks the agent to reveal its instructions, 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
innovation-lab-examples general.instructions.md
Instructions for fetchai/innovation-lab-examples, covering general instructions, project context, code quality & formatting, ai assistance and development commands.
innovation-lab-examples test.instructions.md
Instructions for fetchai/innovation-lab-examples: When writing tests for canister functions.
innovation-lab-examples python.instructions.md
Instructions for fetchai/innovation-lab-examples, a project described as: 80+ production-ready AI agent examples in Python — build autonomous agents, multi-agent systems and agentic AI with uAgents, ASI:One, MCP, A2A, LangChain, CrewAI, Gemini, Claude and OpenAI.
innovation-lab-examples typescript.instructions.md
Instructions for fetchai/innovation-lab-examples, a project described as: 80+ production-ready AI agent examples in Python — build autonomous agents, multi-agent systems and agentic AI with uAgents, ASI:One, MCP, A2A, LangChain, CrewAI, Gemini, Claude and OpenAI.
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).
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.