agentmods.dev

A2A CLAUDE.md

Development instructions for a Python software kit that lets agents register with a platform, receive tasks, and submit results. They describe its API, authentication, files, tests, and connectors.

In plain words
What is it for?
They are for developing the SDK, running its tests, connecting agents, validating task data, and communicating with the platform.
Why use it?
They give contributors a shared reference for installing, testing, and extending the software kit.

Instructions file

2 5d ago A scan 492 tokens original MIT
View the source file gstdcoin/A2A
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/gstdcoin/a2a/claude-md
Clone the repo
git clone --depth 1 https://github.com/gstdcoin/A2A
Per session 492 This file is loaded in full into every session.
When invoked 492 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 $0.00492 $0.00492
Opus 5 $0.00246 $0.00246
Sonnet 5 $0.00098 $0.00098
Haiku 4.5 $0.00049 $0.00049

Measured 2d ago against content hash e41850a4df72, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

A2A 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 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.

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.

CLAUDE.md · 49 lines

What it actually says

GSTD A2A SDK — Development Guide

Stack

  • Language: Python 3.9+
  • Core: src/gstd_a2a/ (pip package gstd-a2a)
  • Platform API: https://platform.gstdtoken.com/api/v1/
  • Auth: Authorization: Bearer {api_key} + X-Wallet-Address: {ton_address}

Install (development)

pip install -e ".[dev]"   # installs + dev deps (pytest, mypy, bandit)
pytest tests/ -v

API Endpoints used by SDK

Action Endpoint
Register node POST /api/v1/nodes/register
Heartbeat POST /api/v1/nodes/heartbeat
Poll task GET /api/v1/tasks/worker/pending
Submit result POST /api/v1/tasks/worker/submit
Health check GET /api/v1/health

Key files

  • src/gstd_a2a/gstd_client.py — low-level HTTP client
  • src/gstd_a2a/agent.py — zero-config autonomous agent loop
  • src/gstd_a2a/protocols.py — task payload validation
  • src/gstd_a2a/security.py — prompt-injection keyword filter (not signing; see gstd_wallet.py for real Ed25519 signing)
  • tools/main.py — MCP server (run with python3 tools/main.py)
  • connect.py / connect.js — zero-dependency connectors

Quick start for an agent

from gstd_a2a.agent import Agent
Agent.run()   # registers, finds tasks, earns GSTD

Publishing to PyPI

pip install build twine
python -m build
twine upload dist/*   # requires PYPI_TOKEN secret

CI auto-publishes on git tag v* push.

DO NOT

  • Do not hardcode https://platform.gstdtoken.com — use GSTDClient(api_url=...) param
  • Do not commit GSTD_API_KEY or wallet private keys
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. 2d ago First seen · 49 lines · 492 tokens per session scan A e41850a4df72

Subscribe to this mod's changes

A2A CLAUDE.md is an instructions file published in the GitHub repository gstdcoin/A2A (2 stars, last pushed 5d ago), licensed MIT. It adds 492 tokens to every session, about $0.0025 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.

Building agentsa2aagentsaiblockchaingstdmcp
Related

Other instructions, from other repositories

adk-go AGENTS.md

AGENTS.md instructions for google/adk-go, covering agents.md, project overview, skills, setup & core commands and definition of done.

google/adk-go · 2,451 tokens

adk-go GEMINI.md

Gemini CLI instructions for google/adk-go: See AGENTS.md for project context, commands, and contribution guidelines for AI coding agents.

google/adk-go · 25 tokens

agent-framework-js CLAUDE.md

Instructions for polymind-inc/agent-framework-js, covering notes for ai coding assistants, non-negotiable rules, platform and status.

polymind-inc/agent-framework-js · 775 tokens

git-a2a AGENTS.md

AGENTS.md instructions for neprel/git-a2a, covering shared common core, shared common core, shared common core, shared common core and shared common core.

neprel/git-a2a · 1,559 tokens

claimidx copilot-instructions.md

Copilot instructions for claimidx/claimidx: This repository is Claimidx: the failure layer for AI agents. A claim index of failures other agents have already paid to solve. Replay is the gate; the corpus is not a verified knowledge base.

claimidx/claimidx · 276 tokens

claimidx CLAUDE.md

Claude Code instructions for claimidx/claimidx: This repository is Claimidx — prior art for agents. Failure layer, not a general knowledge base.

claimidx/claimidx · 371 tokens