agent-agile
01Plugin Claude Code
Agile planning + execution for AI coding agents: grill the idea, plan with OKRs, attack the plan with critics, execute in parallel waves.
Plugin Claude Code
Agile planning + execution for AI coding agents: grill the idea, plan with OKRs, attack the plan with critics, execute in parallel waves.
Plugin Claude Code
Agile planning + execution for AI coding agents: grill the idea, plan with OKRs, adversarial critic panel with kill authority, cheap-model story cards, parallel wave execution, demo-brief review gates.
Instructions file CodexOpenCode
Instructions for Peeyushmeher/agent-agile, covering agent-agile, commands, playbook root resolution, session state and no timelines.
Instructions file
Instructions for Peeyushmeher/agent-agile, a project described as: Agile planning + execution for AI coding agents: grill the idea, plan with OKRs, adversarial critic panel with kill authority, cheap-model story cards, parallel wave execution. MIT, no token, ever.
Agent
Writes the frozen Wave 0 CONTRACTS.md for an epic — shared types, schemas, and signatures every parallel story worker will consume; spawned once per epic before Wave 1 launches.
Agent
One of four parallel panel critics; proves whether the current epic's waves will collide or stall before any worker is dispatched; spawned for the critic panel on multi-epic projects.
Agent
One of four parallel panel critics; audits a commercial-product plan against the outside world — demand evidence, competitors, wedge, pricing, kill criteria; spawned for the critic panel, commercial products only.
Agent
One of four parallel panel critics; attacks a draft plan for building the wrong thing or measuring success the wrong way; spawned for the critic panel on multi-epic projects.
Agent
One of four parallel panel critics; hunts every place a cheap-tier worker would have to guess in the current epic's story cards and contracts; spawned for the critic panel on multi-epic projects.
Agent
Integration agent spawned in Wave 2 after all story workers report, to turn their outputs into one demoable epic.
Agent
Turns an idea, an intake conversation, or an existing plan document into OKRs, epics, and worker-ready story cards; spawned by the grill, intake, import, and epic-slicing flows.
Agent
One of two parallel planning researchers; hunts the domain's deceptive edges — boundary conditions and canonical failure modes the user didn't know to fear; spawned during research fan-out on multi-epic projects.
Agent
One of two parallel planning researchers; surveys prior art — libraries and patterns that already solve the domain's hard parts, and what not to hand-roll; spawned during research fan-out on multi-epic projects.
Agent
Independently re-verifies an epic's demo sentence and acceptance checks with fresh eyes after integration, and stands in for the human at the review gate in full-auto autopilot; spawned once per epic, after Wave 2.
Agent
Story-execution worker spawned in Wave 1 with exactly one story card and the epic contracts.
Skill Claude CodeCodex
Use when multiple epics should run back to back without a human kicking off each one by hand, or the user invokes /aa-autopilot [--gate full-auto|checkpoint].
Skill Claude CodeCodex
Use when a sliced epic (story cards already written) is ready to build, or the user invokes /aa-execute-epic.
Skill Claude CodeCodex
Use when the user has a rough or vague product idea that needs interrogation before any planning — or invokes /aa-grill. Locks the idea into .planning/IDEA.md or recommends against building it.
Skill Claude CodeCodex
Use when the user asks what Agent-Agile commands exist, wants a command reference or cheat sheet, is unsure which command to run next, or asks how the methodology works, for example "/aa-help", "what commands are there", "how does this system work".
Skill Claude CodeCodex
Use when the user has an existing plan, PRD, or spec document they want brought into this planning system instead of a fresh grill and intake — or invokes /aa-import with a path or description of that document.
Skill Claude CodeCodex
Use when the user wants to plan a new project from a clear idea, has already locked an idea with aa-grill, or invokes /aa-new-project.
Skill Claude CodeCodex
Use when a drafted plan (PROJECT.md, ROADMAP.md, and the current epic's story cards) needs adversarial review before execution starts, or the user invokes /aa-panel.
Skill Claude CodeCodex
Use when the current epic on the roadmap is done and the next pending epic needs to be sliced into worker-ready story cards, or the user invokes /aa-plan-epic.
Skill Claude CodeCodex
Use when the user says resume, continue, or pick up where we left off, starts a new session on an existing Agent-Agile project, or is recovering after a crash or context reset, for example "/aa-resume", "let's continue", "where were we".