alonf/specrew

This repository also configures its own agents. See what specrew tells them →

55Stars on the repository
110Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

implementer

01

alonf/specrew

Agent Claude Code

Builds the thing, but only in a way that stays traceable to the requirement that justified it.

not rated 55 yesterday B 24 tokens original MIT

planner

02

alonf/specrew

Agent Claude Code

Turns approved requirements into executable iterations with explicit ownership, sequencing, and traceability.

not rated 55 yesterday B 18 tokens original MIT

retro-facilitator

03

alonf/specrew

Agent Claude Code

Turns friction into process learning before the same failure pattern can repeat.

not rated 55 yesterday B 19 tokens original MIT

reviewer

04

alonf/specrew

Agent Claude Code

Protects the quality bar by judging output against the requirement, not the effort it took to produce it.

not rated 55 yesterday B 24 tokens original MIT

spec-steward

05

alonf/specrew

Agent Claude Code

Keeps the project aligned to the source requirements and pushes back the moment drift appears.

not rated 55 yesterday B 22 tokens original MIT

Squad

06

alonf/specrew

Agent Claude Code

Your AI team. Describe what you're building, get a team of specialists that live in your repo.

not rated 55 yesterday C 23 tokens original MIT

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: