Developer Tools Codex plugins

Plugin name

Hyperhuman Agent Workspace

Publisher subtitle

Run ASE + UMA adsorption

Publisher capabilities · listing

…gn conversation state, workflow state, durable preferences, and application memory Add guardrails, human approvals, least-privilege controls, and prompt-injection defenses Create agent evaluations for task success, tool use, trajectories, side effects, latency, and cost Design tracing and observabil…

Publisher capabilities · listing

Review agent skill behavior Explain skills in clear language Decide how much a human must read before approving

Publisher keywords · package

…al-design visual-design-contract color-contrast uncertainty export diagrams operational-workspaces humanitarian geopolitical

Publisher name · package

Human-Agent-Society

Publisher description

…ate the issue. Built for support and technical teams, Birdie reduces back and forth and helps both humans and AI troubleshoot customer issues faster.

Publisher full description

…build runnable voice features and generate MP3/WAV files with CastReader Voice API estimates and resumable jobs. Developer API credit is separate from consumer membership. This answer-reading release supports English and highlights the formatted reading page.

Publisher description

…d to reject on report evidence. Free domain scans and a free monitoring trial. Every DNS change is human-approved. Fix records are generated deterministically and RFC-validated, never guessed by AI; SPF is diagnosed, never rewritten. Twenty tools: scan a domain (SPF, DKIM, DMARC, MX, DNS health, bla…

Publisher full description

…plugin to connect to Kora SaaS, design approval-aware workflows, use available extensions, connect human and agent work, and explicitly install or operate self-managed Kora when needed—with observability, auditability, and controlled change built in.

Publisher description

…ve shared context, query authorized data, preview changes, and run permission-checked actions with human approvals where required.

Publisher description

Mnemom is trust infrastructure built for agents, not just the humans who run them. In one chat you can look up an agent's Continuous Trust Rating — the score, the grade, and the accountability evidence behind it — and confirm it's cryptographically signed, not me…

Publisher description

…materials for change evidence, requirement alignment, testing, risks, rollback, and readiness for human review. It does not access repositories, run tests, approve, or merge pull requests.

Publisher description

…uction with CI/CD, observability, release safety, migrations, security, performance, rollback, and human-only operational steps.

Publisher full description

…only; implementation, verification, and production changes require separate tools and accountable human review.

Publisher description

…ses, and releases, resolve tokens for implementation, and prepare governed changes on branches for human review.

Publisher description

…ons, issues, docs, product, and production systems so agents can complete work correctly with less human intervention. Coding agents know the code. They do not know why it was written that way, which of two conflicting docs is current, what a ticket decided, or what production is doing right now. Un…

Publisher full description

ZzzOps gives autonomous coding agents a reviewed, prioritized, and resumable agentic-engineering loop for repository bootstrapping and durable goals in GitHub Issues. It coordinates implementation only under reviewed project policy.