797 tagged agentic-workflow, measured the same way as everything else here.
Browse within: agentic-framework 194agentic 151claude-code-plugin 129neural-networks 116swarm-intelligence 116agent-orchestration 95antigravity 85agentic-systems 83agentic-coding 81agent-catalog 71ai-tooling 71agentic-development 66ai-assistant 60ai-coding 58
Command
A project-status command for an IPD-OMO development project. It reads the project's state file and reports progress, review status, team tasks, risks, and suggested decisions.
Command
A command that runs a staged technical review process involving quality, testing, architecture, and requirements checks before a release decision. IPD-OMO is the process named in the add-on; its specialized role names are not explained further in the input.
hybridlabor-api/bdb-dev-optimized-agent-skills
Command Claude Code
Complete a security review of the pending changes on the current branch.
Command Codex
Challenge a pull request with an independent second opinion from another model.
Command Codex
Forensic audit of an implementation against its authoritative specification.
Command Codex
Architectural review of a specification before implementation begins.
Command Claude Code
Run a comprehensive code quality audit across the entire repo. Dynamically analyzes source code for dead code, complexity, duplication, error handling gaps, type safety issues, class cohesion, and method size. Creates GitHub issues for findings so HydraFlow can process them.
Command Claude Code
Run a comprehensive integration test audit across the entire repo. Dynamically discovers external dependencies in source code, inventories existing integration tests, identifies coverage gaps, flags ugly/outdated tests, and creates GitHub issues for findings.
Command Claude Code
Run a comprehensive test quality audit across the entire repo. Analyzes test naming, structure, hygiene, factory usage, fluent builder patterns, anti-patterns, coverage gaps, and flaky patterns. Creates GitHub issues for findings so HydraFlow can process them.
Command Claude Code
Run eval suite and report regressions vs. main baseline.
Command Claude Code
Scaffold a new worker agent with module, prompt v1, schema, tests, and eval stub.
Command Claude Code
Staff-engineer code review: security, regressions, prompt diffs.
Command
Use when an agent should investigate a defect, regression, flaky test, or incident-like failure with evidence, hypotheses, verification, and recurrence prevention.
Command
Use when an agent should run a Discover -> Define -> Develop -> Deliver workflow before implementing a meaningful feature.
Command
Use when an agent should autonomously escalate a hard task into a recursive session, prefer Typed RLM first, and only fall back to bounded structured analysis when needed.
punkadillo/figma-code-composer
Command Claude Code
Build NEW components/icons/tokens from a Figma design via the full figma-coordinator pipeline (fetch → tokens → icons + components in parallel → stories + tests in parallel).
punkadillo/figma-code-composer
Command Claude Code
Generate or repair ONLY icons from a Figma design via the figma-coordinator pipeline (figma-fetcher → icon-generator). No components, tokens, stories, or tests.
punkadillo/figma-code-composer
Command Claude Code
Generate or refresh ONLY design tokens from a Figma design via the figma-coordinator pipeline (figma-fetcher → token-builder). No components or icons.
Command Claude Code
Review analytics and recent commits, then create tasks.
Command Claude Code
Pick up one approved task, implement the fix, and close it.
Command Claude Code
Full SEO check — technical + on-page audit plus Google Search Console data, then create tasks with concrete fixes.
codeverbojan/claude-code-kickstart
Command Claude Code
New feature playbook — plan, build in phases, verify each phase.
codeverbojan/claude-code-kickstart
Command Claude Code
Analyze the codebase and auto-generate CLAUDE.md Section 10 project config.
codeverbojan/claude-code-kickstart
Command Claude Code
Analyze the codebase and extract real patterns into patterns.md.
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: