project management agents

codervisor/leanspec

Agent

Comprehensive guidelines for maintaining high-quality documentation in the LeanSpec documentation site.

FrkAk/piyaz

Agent

Use when a Piyaz project exists with a description but few or no tasks, and the user wants it broken into an implementable graph (project-level decomposition). Triggers: "decompose", "break this down", "create tasks", "turn this into tasks", "give me a task list", "plan out the work", "how should I build this". Do not…

FrkAk/piyaz

Agent

Use when the current repo has existing code but no Piyaz project that matches it, and the user wants to adopt Piyaz on day N. Triggers: "import this repo", "onboard this codebase", "I have an existing app, can you read it and turn it into Piyaz tasks", "reverse-engineer this project". Do not use when no code exists…

FrkAk/piyaz

Agent

Dispatched after a task lands at inreview to produce a structured CTO-grade verdict on the work and its PR. Two invocation paths: composer Phase 4 (orchestrator dispatches after the implementer's inreview write, surfaces the verdict to HOTL, stops), and direct mode from the piyaz skill on requests ("review VF-N"…

arch-team/devpace

Agent

Analyst perspective agent for devpace. Handles metrics collection, retrospectives, and trend analysis. Data analysis with write capability for dashboards and insights.

arch-team/devpace

Agent

Engineer perspective agent for devpace. Handles CR implementation, quality gates, and code changes. Full file access for development work.

arch-team/devpace

Agent

Product manager perspective agent for devpace. Handles iteration planning, change management, and business alignment. Analysis with write capability for planning and change execution.

mattwynne/yaks

Agent

Independent deep technical review using Anthropic Claude model.

mattwynne/yaks

Agent

Fast codebase recon that returns compressed context for handoff to other agents.

mattwynne/yaks

Agent

General-purpose subagent with full capabilities, isolated context.

wanghao9610/STAR

Agent

Blind second read of finished work against a rubric — scores it, decides nothing, and was not present for the conversation that produced it.

wanghao9610/STAR

Agent

Read-only collection pass for a STAR skill — reads the exact files it was given and returns the form it was given, filled in.

wanghao9610/STAR

Agent

Executes one step of a STAR execution plan under a written dispatch brief — changes only the files the brief names.

rmolines/fractal-loop

Agent

Evaluates a fractal objection: given a challenge and its existing children, finds the strongest reason the challenge still stands — or declares it refuted.

rmolines/fractal-loop

Agent

Evaluates a fractal predicate: given the predicate and its existing children, decides the next step — propose a new child, declare complete, classify as leaf, or mark unachievable.

rmolines/fractal-loop

Agent

Executes the full sprint cycle (planning → delivery → review → ship) for a leaf predicate. Runs internally with no human gates — the review is the quality gate.

thrashr888/AllBeads

Agent Claude Code

Agent that helps onboard repositories into AllBeads.

thrashr888/AllBeads

Agent Claude Code

Agent that plans new projects without implementing code.

thrashr888/AllBeads

Agent Claude Code

Autonomous agent that finds and completes ready tasks across contexts.

rjroy/vibe-garden

Agent

Analyzes file-based backlog items for quality and readiness, scoring each item on definition quality (clarity, completeness, acceptance criteria) and recommending the best 2-3 options to work on next. Combines priority, size, and definition quality for smart recommendations. Use when analyzing project items for the…

rjroy/vibe-garden

Agent

Scans codebase to assess issue relevance based on current state. Compares issue descriptions against actual implementation to identify stale issues, potentially resolved items, and issues with increased relevance. Use when reprioritizing project backlog.

rjroy/vibe-garden

Agent

Reviews implementation plans with fresh context to identify gaps, infeasible steps, and scope creep. Invoke after completing a plan. Works with or without a spec -- checks requirement coverage when a spec exists, checks goal alignment when it doesn't.

vector233/repo-continuity

Agent Claude Code

Use only for ambiguous high-impact cross-module design, major migrations, and difficult root-cause analysis after ordinary investigation is insufficient.

vector233/repo-continuity

Agent Claude Code

Use proactively for read-only file and symbol discovery, execution tracing, log inspection, and evidence gathering before a change or review. Use @explorer when a cost-controlled exploration pass is required.