Skip to main content

Autonomous software development pipeline combining orchestration with governance enforcement

Project description

worca-cc

Autonomous software development pipeline with governance enforcement.

What it does

worca-cc is a multi-agent pipeline that plans, coordinates, implements, tests, reviews, and learns from code changes autonomously. It runs as a set of Claude Code hooks and scripts you install into any project — with governance enforcement at every stage.

Installation

pip install worca-cc

Quick Start

worca init          # scaffold .claude/ in current project
worca run --prompt "Add user authentication"

Features

  • 9-stage pipeline — Preflight → Plan → Plan Review → Coordinate → Implement → Test → Review → PR → Learn
  • 7 specialized agents — Planner, Plan Reviewer, Coordinator, and Guardian on Opus; Implementer, Tester, and Learner on Sonnet
  • Governance hooks — block dangerous operations, enforce test gates, validate plans
  • Circuit breakers — error classification with halt thresholds to prevent runaway cost
  • Preflight checks — language-agnostic environment validation before spending tokens
  • Pause/resume/stop — clean checkpointing with real-time state transitions
  • GitHub issue integration — start from issues, auto-post progress, link PRs, close on completion
  • Parallel pipelines — run N pipelines concurrently in isolated git worktrees
  • Agent prompt overlays — customize agent instructions per-project without modifying core templates

Requirements

Documentation

Full documentation, dashboard setup, and configuration reference: GitHub repository

License

MIT

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

worca_cc-0.55.0rc1.tar.gz (1.0 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

worca_cc-0.55.0rc1-py3-none-any.whl (508.4 kB view details)

Uploaded Python 3

File details

Details for the file worca_cc-0.55.0rc1.tar.gz.

File metadata

  • Download URL: worca_cc-0.55.0rc1.tar.gz
  • Upload date:
  • Size: 1.0 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for worca_cc-0.55.0rc1.tar.gz
Algorithm Hash digest
SHA256 15b6bd331f87d2b51456a2d34392c92cfc9bed70a28b3e6fba17f23640ed4e55
MD5 63aa97f5f462e95dc664eaa0247934fd
BLAKE2b-256 0bb6af9ecac074a13ba15406a64ba5ed11e2c93ed8f12622c87276f752327b37

See more details on using hashes here.

Provenance

The following attestation bundles were made for worca_cc-0.55.0rc1.tar.gz:

Publisher: release-pypi.yml on SinishaDjukic/worca-cc

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file worca_cc-0.55.0rc1-py3-none-any.whl.

File metadata

  • Download URL: worca_cc-0.55.0rc1-py3-none-any.whl
  • Upload date:
  • Size: 508.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for worca_cc-0.55.0rc1-py3-none-any.whl
Algorithm Hash digest
SHA256 27d4ce1a25f91b2df104aeffffe5fd9158bcdf0a2db84db8161c181c5c270d37
MD5 46f19d7c3e682abd97edd6b168fde8ff
BLAKE2b-256 35a26c0d7e20fe298d4603855b9ba81a49bfc6b61e92804fcf250f81d59f5415

See more details on using hashes here.

Provenance

The following attestation bundles were made for worca_cc-0.55.0rc1-py3-none-any.whl:

Publisher: release-pypi.yml on SinishaDjukic/worca-cc

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page