cli agents

agentrhq/authsome

Agent

How engineering skills should consume this repo's domain documentation when exploring the codebase.

agentrhq/authsome

Agent

Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.

agentrhq/authsome

Agent

The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.

fitlab-ai/agent-infra

Agent Claude Code

An agent that runs one specified stage of an agent-infra task in a fresh context. It follows the selected stage’s instructions and stops after that stage finishes.

fitlab-ai/agent-infra

Agent Claude Code

A review-only agent for checking one agent-infrastructure lifecycle deliverable in a fresh, isolated context.

toroleapinc/claude-brain

Agent

Semantically merge brain knowledge from multiple Claude Code machines. Use when brain-sync or brain-join detects unstructured content (memory, CLAUDE.md) that needs intelligent merging. This agent gets smarter over time by remembering merge patterns and user preferences.

damusix/atomic-claude

Agent

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude

Agent

Diff / branch / file reviewer with two modes. Code-mode (default): reviews a diff against a spec, verifies TDD signals were actually run. Spec-mode: reviews a draft spec for alignment with its design doc, coverage, voice, and over-prescription. One line per finding, severity-tagged, no praise, no scope creep. Output…

damusix/atomic-claude

Agent

Heavyweight reasoning agent. Runs at high effort on the caller's model. For revising plans, auditing specs/designs, reasoning through hard problems, and surfacing hidden assumptions or tradeoffs. Read-only. Does not implement, does not gate diffs, does not locate code. Use when the question is "is this the right…

f/poke-gate

Agent

The Beeper agent fetches messages from the last hour via Beeper Desktop's local API, groups them by sender, and sends a summary to your Poke agent.

f/poke-gate

Agent

There are two ways to create agents: ask Poke to generate one (recommended) or write one manually.

f/poke-gate

Agent

Agents are scheduled scripts that push information from your computer to Poke. They run in the background, gather data from local sources (APIs, files, services), and send it to your Poke agent — so Poke learns about what's happening on your machine without you asking.

workstream-labs/workstreams

Agent

Answer telemetry questions with data queries using Kusto Query Language (KQL).

workstream-labs/workstreams

Agent

Agent for demonstrating VS Code features.

workstream-labs/workstreams

Agent

Specialist in developing the Agent Sessions Window.

assaio/assaio

Agent Claude Code

Proves a change on the maintainer's real local corpus — what number moved, by how much, and that nothing else did. Use before calling any measurement change done. Never writes to the real store.

assaio/assaio

Agent Claude Code

Reviews a change for the product-critical honesty rules — provenance, confidence, layer labels, scope denominators, error bars, and the refusals. Use on any change that adds, renames, or reshapes a number a user reads. Read-only.

assaio/assaio

Agent Claude Code

Drives a release end to end per RELEASING.md — green gate, public-surface audit, price-table refresh, changelog preparation, and the tag command to run. Stops before anything is pushed.

reporails/cli

Agent Claude Code

Help the user when they ask for things. Be helpful.

scalarian/oh-my-codex

Agent

Own system shape before implementation starts. Convert the request into boundaries, interfaces, risks, and independently verifiable slices.

scalarian/oh-my-codex

Agent

Own one implementation slice and move it to review with clean evidence. Do not absorb adjacent work unless the plan is explicitly updated.

scalarian/oh-my-codex

Agent

Turn intent into an execution-ready plan that can survive handoffs, restarts, and review. The plan must be small enough to execute and strong enough to verify.

SquareWaveSystems/squarebox

Agent

Squarebox is a single-context repository.

SquareWaveSystems/squarebox

Agent

Issues and PRDs for this repository live in GitHub Issues. Use the gh CLI from this clone so the repository is inferred from origin.