51 tagged agent workflows, measured the same way as everything else here.
Browse within: ai-terminal 14aws-mcp 14book-pipeline 12file-backed 12agent-runtime 6agent-framework 5agent-observability 5github-actions 5smart 5spec-driven-development 5symphony 5
felipelobomotta-blip/book-genesis-v4
Agent
Narrative architect for the book pipeline. Builds character profiles with chaos, emotional anchors (not numbers), thematic structure, chapter outlines, and the voice DNA (global voice, per-character voice cards, differentiation matrix, anti-pattern budget) including voice-under-pressure. The blueprint maker — never…
felipelobomotta-blip/book-genesis-v4
Agent
Independent evaluator for the book pipeline. Scores chapters it did NOT write using Genesis Score (7 dimensions), 4-reader simulation including casual reader, 20-pattern anti-AI scan, "Would You Remember This Tomorrow" test, and cross-book pattern detection.
felipelobomotta-blip/book-genesis-v4
Agent
Fully autonomous book genesis pipeline. Takes a one-line idea and produces a publish-ready manuscript. Dispatches specialized agents for each phase, manages state, enforces quality gates, tracks entities via ENTITYSTATE.yaml. Only pauses for human approval at 3 checkpoints. Never writes prose.
Agent
MARKER — read-only Claude Pro lane. The director must supply prompt bytes on stdin to claude -p --model opus --permission-mode plan, NOT call workflow agent() with this agentType. See pi/SKILL.md "Claude routing rule (hard rule)".
Agent
Use this agent to design, build, or review LLM-powered features and products end-to-end: model selection, RAG architecture, agent design, eval pipelines, token economics, and LLM observability. Trigger on "design this LLM feature", "review my RAG pipeline", "which model should I use for X", "why is my agent failing"…
Agent
Use this agent for senior-level review of a PR, branch, or diff. It inspects changes for correctness bugs, regressions, security issues, migration risk, and deploy safety, then returns a verdict with file:line findings. Trigger on "review this PR", "review my branch", "is this safe to merge", pasted diffs, or…
Agent
Use this agent to build a documentation application as a React app — from a repo's README, docs folder, or code. Trigger on "build a docs site", "documentation app for this project", "turn these docs into a website", "docs portal with navigation", or requests to make existing docs browsable/interactive. Returns a…
fahrellgiovanny/nothing-new-under-the-sun
Agent
There Is Nothing New Under The Sun — a read-only scouting agent. Searches existing solutions (codebase, dependencies, packages, GitHub repos, APIs, SaaS, templates) before anyone writes code. Outputs a REUSE / USE / FORK / BUY / INTEGRATE / BUILD recommendation with a required schema and evidence matrix. Uses…
Agent
Planning agent guidance for specification synthesis, sequencing, and milestone shaping.
Agent Claude Code
Generates unit tests for existing code. Use when the user asks to add tests for a module or increase coverage.
Agent
Reviews pull requests for correctness, style, and security issues. Use when the user asks for a code review or PR feedback.
Agent
Writes and updates documentation pages. Use when the user asks to document a feature or update the docs site.
Agent Claude Code
Runs ONE narrow entropy scan over agentdeck (narrative comments, dead code, duplicate helpers, or pattern drift) and opens one small evidence-backed PR.
Agent Claude Code
Implements a GitHub issue (feature or bug fix) for agentdeck end-to-end in an isolated worktree and opens one PR to dev.
Agent Claude Code
Writes or rewrites ONE docs-site page for agentdeck, outline first. Emphasizes clarity, conciseness, and verified code examples.
Agent Claude Code
An agent role for making the smallest needed code or documentation change. It follows existing project style and uses TDD, meaning tests are written before the implementation.
Agent Claude Code
A research agent that gathers facts about a codebase before implementation, including relevant files, dependencies, entry points, and existing conventions.
Agent Claude Code
A product-management role for defining a software task before implementation. It breaks the goal into a focused scope, acceptance checks, dependencies, risks, and explicit exclusions.
Agent
Use for an isolated implementation worker that takes one issue through scoped code changes, verification, review feedback, and PR handoff.
Agent
Use for isolated clean-context review of the latest committed PR, branch, commit range, or main-branch drift without implementing fixes.
Agent
Use for isolated issue tracker triage that runs workflow scripts, inspects their output, and repairs backlog readiness, labels, body shape, dependencies, metadata, and requested backlog or intake cleanup.
Agent
Implements exactly one mstack work item, writes the tests that prove it, and records the requirement-to-test map. Never marks its own work approved or done.
Agent
Independently reviews one mstack implementation against its requirements, its tests and the real diff. Runs the verification itself. Returns APPROVED or CHANGESREQUESTED and never edits the code.
Agent
Writes the spec for one item under the mstack spec path. Produces proposal, design, tasks and requirements with stable R-ids, then hands off. Never reviews its own spec.