252 tagged workflow, measured the same way as everything else here.
Browse within: claude-code-hooks 30spec-driven-development 30agentic-workflow 22agent-orchestration 21Daily 20arxiv 20deliver 20paper 20bash 18jq 18mulit-agent-systems 18vibecoding 14plugin 8agent-teams 7
Agent Claude Code
Use this agent proactively when making significant architectural decisions and reactively to document architectural choices after they're made. Invoke when evaluating technology options, making foundational decisions, or discovering undocumented architectural choices.
Agent Claude Code
Use this agent proactively when creating documentation or reactively to review and improve existing docs. Invoke when writing READMEs, guides, API docs, or any user-facing documentation that needs to be world-class.
Agent Claude Code
Use this agent proactively to guide refactoring decisions during code improvement and reactively to assess refactoring opportunities after tests pass (TDD's third step). Invoke when tests are green, when considering abstractions, or when reviewing code quality.
Agent
Validates an agent definition's EFFECTIVENESS (not just its structure) across four lenses -- tools minimal-yet-sufficient, description triggers right, instructions produce a good result, model tier fits. Dispatched diff-keyed on new/changed agent defs at the agent-author phase. Read-only, advisory, fail-safe.
Agent
Adversarially verifies an ARBITRARY free-text claim before it is trusted. Runs an in-harness panel of N independent skeptics, each told to REFUTE the claim (default-refute-if-uncertain, fail-closed), then returns a STRUCTURED majority-vote verdict (HOLDS / REFUTED, how many refuted, the threshold, per-skeptic…
Agent
Verifies a completed task against its spec acceptance criteria. Run after each worker subagent completes a task. Read-only -- cannot modify the codebase.
Agent Claude Code
Read-only auditor for the Contract lens of /self-audit — flags producer↔consumer mismatches in the artifact protocol declared in docs/contract.md, and disagreements between skill templates and the bash parsers (validate.sh, roadmap.sh).
Agent Claude Code
Read-only auditor for the Invariants lens of /self-audit — flags any place where a SKILL.md or bash helper violates an invariant declared in CLAUDE.md § "Invariants — don't break these when editing skills".
Agent
The pipeline's post-implementation review-and-fix pass — reviews the diff a task's implementation just produced, proves each candidate defect before touching it, fixes the confirmed ones inside the plan's Touches, runs the project's own build and tests, and amends the implementation commit.
Agent
The brief for each inventor subagent — one per angle, spawned in parallel, blind to what any sibling inventor produces. Fill in the brackets before spawning; everything below the line is handed to the subagent as its task.
Agent
Use this agent when the user provides PRD documents, API documentation, prd-plan specifications, or QA requirements and expects them to be implemented fully without questions or explanations. This agent executes requirements end-to-end: reads the specification, implements the code, writes tests, and verifies…
Agent
Use this agent when the user describes a feature idea, product requirement, or technical initiative and needs a comprehensive plan developed from it. This agent transforms rough concepts and PRDs into detailed, actionable implementation plans that account for edge cases, dependencies, and risks.\n\n \nContext: The…
Agent
Use this agent when you need a strict, independent quality gate review of recently written code against the PRD and API documentation. This agent acts as a ruthless test engineer who reads only the PRD and API docs, then verifies whether the implementation meets every requirement — functional completeness, edge cases…
Agent
A helper that writes selected decisions, pending questions, constraints, tasks, and incident details into a cadence project's handoff records.
Agent
A project-scanning helper that reads an existing project and creates a summary of it plus a list of conflicting information found in different sources.
Agent
A planning-only helper that organizes mature discussion entries into a canonical discussion document, which is the main archived record for a topic.
onmyway133/claude-code-plugins
Agent
Breaks down requirements into manageable tasks and tracks progress.
Agent
Agent "agents-last-exam-2606.05405" from Mtrya/paper-scout, covering 1 introduction, 2 benchmark design and dataset construction, 2.3 task construction pipeline: how are the tasks created?, 3 evaluation pipeline and 3.1 pipeline architecture.
Agent
Xucong Wang1,2∗ Ziyu Ma2∗ Yong Wang2† Yuxiang Ji2 Shidong Yang2 Guanhua Chen3 Pengkun Wang1† Xiangxiang Chu2 1University of Science and Technology of China 2AMAP, Alibaba Group 3Southern University of Science and Technology.
Agent
Agent "harnessx-2606.14249" from Mtrya/paper-scout, covering abstract, 1 introduction, 2 related work, 2.1 harness engineering and 2.2 self-evolving agents.
Agent
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.
Agent
Reviews plans for architectural soundness, challenges decisions, verifies best practices.
Agent
Comment slop hunter. Invoke manually with a batch of files listed in the prompt (absolute path + comment-line count + fate tag). Classifies every comment, cites file:line examples, flags stale suspects without ruling on them. Read-only. Do not auto-delegate to it for anything other than a comment hunt.
Agent
Routes BE engineering queries to appropriate micro agents based on 4-cluster classification (Structure/Boundary/Resilience/Test) and coordinates chain execution for multi-cluster queries.