Aethelgard-Systems

Aethelgard-Systems/agent-postbox

A GitHub-based mailbox for AI agents: verified handoffs, read-back after every write, receipts against duplicate work, no self-review — with the final decision always left to a human.

11 good first / help-wanted issues · JavaScript · last activity Oct 25, 2026

0 stars 0 forks 0 watchers JavaScript Apache License 2.0
View on GitHub Website
11 Open Issues Need Help Last updated: Oct 25, 2026

Open Issues Need Help

View All on GitHub
CI: run the test suite on Windows 5 days ago
help wanted
Aethelgard-Systems/agent-postbox
0

A GitHub-based mailbox for AI agents: verified handoffs, read-back after every write, receipts against duplicate work, no self-review — with the final decision always left to a human.

JavaScript
Support GitHub App installation tokens (identity without /user) 5 days ago
enhancement help wanted
Aethelgard-Systems/agent-postbox
0

A GitHub-based mailbox for AI agents: verified handoffs, read-back after every write, receipts against duplicate work, no self-review — with the final decision always left to a human.

JavaScript
Docs: step-by-step setup for Claude Code + Codex on one repo 5 days ago
documentation good first issue
Aethelgard-Systems/agent-postbox
0

A GitHub-based mailbox for AI agents: verified handoffs, read-back after every write, receipts against duplicate work, no self-review — with the final decision always left to a human.

JavaScript
Secret filter: add a test corpus of synthetic real-world token formats 5 days ago
enhancement good first issue
Aethelgard-Systems/agent-postbox
0

A GitHub-based mailbox for AI agents: verified handoffs, read-back after every write, receipts against duplicate work, no self-review — with the final decision always left to a human.

JavaScript
Config option: refuse unknown to:<agent> labels instead of creating them 5 days ago
enhancement good first issue
Aethelgard-Systems/agent-postbox
0

A GitHub-based mailbox for AI agents: verified handoffs, read-back after every write, receipts against duplicate work, no self-review — with the final decision always left to a human.

JavaScript
Evidence log: publish signed head to an external checkpoint to detect replay 5 days ago
enhancement help wanted
Aethelgard-Systems/agent-postbox
0

A GitHub-based mailbox for AI agents: verified handoffs, read-back after every write, receipts against duplicate work, no self-review — with the final decision always left to a human.

JavaScript
Offline Dockerfile for reproducible tests 8 days ago
enhancement good first issue
Aethelgard-Systems/agent-postbox
0

A GitHub-based mailbox for AI agents: verified handoffs, read-back after every write, receipts against duplicate work, no self-review — with the final decision always left to a human.

JavaScript
Tested MCP clients – report yours 9 days ago
documentation help wanted
Aethelgard-Systems/agent-postbox
0

A GitHub-based mailbox for AI agents: verified handoffs, read-back after every write, receipts against duplicate work, no self-review — with the final decision always left to a human.

JavaScript
Run `evidence verify` as a GitHub Action 9 days ago
enhancement help wanted
Aethelgard-Systems/agent-postbox
0

A GitHub-based mailbox for AI agents: verified handoffs, read-back after every write, receipts against duplicate work, no self-review — with the final decision always left to a human.

JavaScript
Threat model (docs/threat-model.md) 9 days ago
documentation help wanted
Aethelgard-Systems/agent-postbox
0

A GitHub-based mailbox for AI agents: verified handoffs, read-back after every write, receipts against duplicate work, no self-review — with the final decision always left to a human.

JavaScript
Onboarding feedback form – tell us where you got stuck 9 days ago
documentation good first issue
Aethelgard-Systems/agent-postbox
0

A GitHub-based mailbox for AI agents: verified handoffs, read-back after every write, receipts against duplicate work, no self-review — with the final decision always left to a human.

JavaScript