saga

Agent skill from warpdotdev/common-skills.

warpdotdev 146 ↓ 7.2k MIT updated 27d ago

Claude Code

View source ↗

What it does

How is the program run/launched for manual or interactive verification?
Delegate, don't implement. Use runagents to launch workers. You coordinate; you do not write feature code yourself. This is what protects your context.
Never commit or open PRs unless the user asks; follow the repo's version-control rules when you do.
Keep the spec tree current — if implementation forces a change to scope or criteria, update the relevant spec file rather than letting it drift.
For very large sagas (≈10+ concurrent workers), prefer remote execution so you don't exhaust the user's machine.
Don't expose internal worker agent IDs in user-facing summaries unless asked.
references/continuing-a-saga.md — how a fresh orchestrator picks up an existing saga directory and resumes safely. Read when asked to continue/resume a saga.

Requirements & configuration

Configuration: PROGRESSSAGAMILESTONE

Derived from the skill's own SKILL.md documentation · extracted 2026-07-23

Source

Repository: https://github.com/warpdotdev/common-skills

saga FAQ

What does the saga skill do?

Run an autonomous, spec-driven development "saga" for medium-to-large features using an orchestrator agent and a fleet of worker subagents. Use this skill whenever the user invokes /saga, asks to autonomously build a sizable feature end-to-end with minimal human intervention, wants a comprehensive spec broken into milestones and tasks with airtight validation criteria before parallelized implementation, or wants an orchestrator to delegate implementation to worker agents while preserving its own context window. Trigger on phrases like "run a saga", "autonomously implement this feature", "spec it out then build it with subagents", "orchestrate this big feature end-to-end", or "build this with workers and validate each step". Also use this skill when asked to continue, resume, or pick up an existing saga from its saga directory (e.g. under ~/.sagas). How is the program run/launched for manual or interactive verification? Delegate, don't implement. Use runagents to launch workers. You coordinate; you do not write feature code yourself. This is what protects your context.

What does saga require?

Configuration keys: PROGRESS, SAGA, MILESTONE.

How do I install saga?

Run: npx -y skills add https://github.com/warpdotdev/common-skills --skill saga --agent claude-code — the source lives at github.com/warpdotdev/common-skills.

Maintain saga?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

[![saga on getagentictools](https://getagentictools.com/badge/skills/warpdotdev-common-skills-saga.svg)](https://getagentictools.com/skills/warpdotdev-common-skills-saga?ref=badge)

npx agentictools info skills/warpdotdev-common-skills-saga

The second line is the CLI lookup for this page — handy in READMEs and docs.