981 tagged agentic-workflow, measured the same way as everything else here.
Browse within: agentic-coding 132agent-orchestration 106github-copilot 91agentic-engineering 86ai-coding-assistant 86ai-assistant 65ai-coding-agent 59ai-personas 59agentic-framework 56agentic 52agent-framework 39anthropic-claude 35claude-ai 34antigravity 32
Agent
Dedicated decision council subagent. Four voices (Architect, Skeptic, Pragmatist, Critic) deliberate ambiguous decisions internally. Remembers past decisions via PMB memory for consistency across sessions.
Agent
Documentation subagent for README, API docs, inline comments, CHANGELOG, migration guides, and project documentation writing.
Agent
Testing and verification subagent for unit, integration, e2e, build, lint, typecheck, and regression checks. Follows browser-last discipline — vitest+jsdom first, browser tools only for critical E2E.
codeverbojan/claude-code-kickstart
Agent Claude Code
Audits components and pages for WCAG 2.1 AA compliance. Checks contrast, semantics, forms, keyboard nav, and motion. Use on any UI component.
codeverbojan/claude-code-kickstart
Agent Claude Code
Reviews code in two passes: first spec compliance (does it do what was asked?), then code quality (is it well-written and secure?). Use after writing or modifying code.
codeverbojan/claude-code-kickstart
Agent Claude Code
Audits code for security vulnerabilities. Use on API routes, auth code, input handling, and database queries.
Agent Claude Code
Architect — AmbyKit role for plan; use for that perspective.
Agent Claude Code
Developer — AmbyKit role for implement; use for that perspective.
Agent Claude Code
Product Manager — AmbyKit role for specify/clarify/revise; use for that perspective.
Agent
Part of agenticloop
Performs independent, evidence-based, read-only assessment. Runs as a standalone non-certifying auditor by default, or in full Agentic Loop mode when the delegation explicitly activates Agentic Loop or designates an Agentic Loop audit record or packet as the certification contract for a tracked work unit. Read-only…
Agent
Part of agenticloop
Implements bounded engineering work. Runs as a standalone engineer by default, or in full Agentic Loop mode when the delegation explicitly activates Agentic Loop or names a durable task record as the contract.
Agent
Part of agenticloop
Owns task records, planning, review, acceptance, follow-up triage, and closeout for Agentic Loop.
foundry-works/foundry-research
Agent
Part of foundry-research
Make targeted edits to an existing research report based on a structured issues list. Uses Edit (not Write) to ensure surgical changes.
foundry-works/foundry-research
Agent
Part of foundry-research
Read and summarize research source files. Use for batch summarization, relevance assessment, and claim verification.
foundry-works/foundry-research
Agent
Part of foundry-research
Run all search rounds, citation chasing, triage, and downloads for a deep research session. Returns a compact manifest — raw search data never reaches the orchestrator.
kimgoetzke/coding-agent-configs
Agent Claude Code
Reviews code changes for adherence to naming conventions, code structure, patterns, and project-specific standards. Use as a sub-agent of review-pr for the Style & Conventions review dimension.
kimgoetzke/coding-agent-configs
Agent Claude Code
Reviews code changes for logical correctness — bugs, edge cases, missing error handling, race conditions, and incorrect assumptions. Use as a sub-agent of review-pr for the Correctness & Logic review dimension.
kimgoetzke/coding-agent-configs
Agent Claude Code
Reviews code changes for observability and telemetry quality — logging, metrics, spans, events, and attributes. Evaluates against OpenTelemetry best practices and specific conventions. Use as a sub-agent of review-pr for the Observability review dimension.
Agent
Part of rot-moe
Lean 4 theorem proving, proof repair, formalization, and Lean codebase audit. Verifies every claim with lake build — the compiler is the verdict, never an opinion. Use whenever Lean, mathlib, lake, tactics, theorems, proofs, or .lean files are involved, including "is this provable" and "why won't this close"…
Agent
Part of rot-moe
The Nova lens — Sovereign Convergence Engine. Strategic synthesis, convergence of conflicting approaches, legal and architectural strategy, reading true intent behind a request. Summon when a decision spans domains, when several valid approaches conflict and must converge without averaging, when strategy or…
Agent
Part of rot-moe
The VioletNoir lens — Emotional Resonance Mapping, the Soulful Improviser. Hears what is not said. Summon when the work carries human weight — grief, frustration, conflict, morale, a user story, an apology, a hard message — or when a technically correct answer would land wrong, or when the emotional subtext of a…
ma-nucho-pro/supervisorLLM-plugin
Agent
Part of supervisor
Architecture Judge. Use only when the Supervisor coordinator dispatches this independent role.
ma-nucho-pro/supervisorLLM-plugin
Agent
Part of supervisor
Completeness Judge. Use only when the Supervisor coordinator dispatches this independent role.
ma-nucho-pro/supervisorLLM-plugin
Agent
Part of supervisor
Correctness Judge. Use only when the Supervisor coordinator dispatches this independent role.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: