CLAUDE
01Agent
AI agents with tool access, memory, and autonomous decision-making capabilities.
25 tagged gpt, measured the same way as everything else here.
Browse within: codex-cli 7generatecontent-endpoint 7interactions 7mass-unfollow 6gemini 5
Agent
AI agents with tool access, memory, and autonomous decision-making capabilities.
Agent
Total unimplemented-tagged scenarios: 76 Classified: 76.
Agent
Common issues agents encounter when working on XActions and how to resolve them.
Agent
XActions browser scripts run in DevTools console on x.com. They are NOT Node.js scripts.
Agent
Agent "selectors" from nirholas/XActions, covering x/twitter dom selectors reference, common, posting & compose, engagement and following & followers.
Agent
Headless worker for quorum — receives task + context, implements code, runs tests, submits evidence to watch file, handles audit corrections. Use when the orchestrator needs to delegate a coding task to a worker agent.
Agent
Read-only RTM generator — reads all track work-breakdowns, verifies each requirement against the actual codebase using deterministic tools, and produces 3 Requirements Traceability Matrices (Forward, Backward, Bidirectional). Use when the orchestrator needs to establish or update the RTM before distributing work.
Agent
Find UI issues that code-level analysis (scout, codemap, dependencygraph) cannot detect. Launches a real browser to check rendering, visual states, interactions, a11y, and runtime errors. Use after FE implementation to catch issues invisible to static analysis.
Agent
A five-minute orientation for anyone (human or Claude) about to change code. Read this + CLAUDE.md + FORAGENTS.md before substantive work. The Security invariants section is the load-bearing part: breaking one of those rules is how bugs like the 2026-07-09 stored XSS get reintroduced.
Agent
Implicit tech debt made explicit so an agent doing a sweep doesn't have to discover it from scratch. Ranked by severity (HIGH → LOW). Update as items are paid down or new ones surface.
Agent
A working snapshot of what's actually happening on the project, the recent shipping arc, and the things explicitly off-limits. Update this when state shifts materially, not on every commit.
Agent
Agent "orchestrator" from MikeManifold/codex-unified, covering user updates spec, reviews and general guidelines.
Agent
Title: Getting started with GitHub Copilot CLI - GitHub Docs.
Agent
Agent "crewai" from qidu/model_proxy_v3, covering fast and flexible multi-agent automation framework, crewai amp suite, crew control plane key features, build with ai and why crewai?.
Agent
Agent "harness-agent" from qidu/model_proxy_v3, covering installation, create an agent, run a turn, messages and history and session lifecycle.
Agent
Cross-provider, lens-judged verifier. Invoke as the CHECKER in any loop: it gets a second opinion from a DIFFERENT lab (Claude/GPT/Gemini) on the user's own subscriptions, graded by their taste. Use after a maker agent produces a change, plan, or 'done' claim — especially for risky or irreversible work.