Harness Hub
All open source

claude-code-workflows

Claude Code workflows that stay on an approved outcome

shinpr/claude-code-workflows

Maintained by shinpr

Development workflows for Claude Code that keep broad exploration focused on an outcome you approved. Repository topics include agent skills, subagents, code review, and LLM orchestration.

View on GitHub

Activity

Last push
· yesterday
Latest release
v0.31.1
· yesterday
Last 90 days
20+ releases
  1. v0.31.1Release: v0.31.1

    · yesterday

    Work Plan tasks take their verification method and Verification Focus from any governing source they cite, such as a UI Spec, not only the Design Doc.

  2. v0.31.0Release: v0.31.0

    · 10d ago

    What's Changed Executors and designers own how the codebase is built and maintain what they leave behind. The outcome, requirements, and non-goals stay with the user's recorded decisions. Agents find existing code with the same responsibility through its position, role, input,…

  3. v0.30.0Release: v0.30.0

    · 2w ago

    What's Changed Large changes are reviewed in units of Work Plan tasks, with at most 3 code-reviewer calls running at once. Each reviewer reads its unit in full. Medium changes keep one reviewer. code-reviewer no longer lists every acceptance criterion or maps the whole change…

  4. v0.29.6Release: v0.29.6

    · 2w ago

    What's Changed Work Plan tasks cover only repository work the executor completes and verifies during implementation. Plans no longer add tasks, notes, or caveats for work outside the repository change. After the first codebase analysis, the workflow stops once when existing…

  5. v0.29.5Release: v0.29.5

    · 2w ago

    What's Changed When requirements leave a quality level unset (performance, freshness, consistency, availability, or protection beyond the required trust boundary), design selects the lowest level that still delivers the outcome and records it. ADR and Design approval stops show…

Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.

Featured

openclaw/openclaw

The viral open-source personal AI assistant that really does things.

Maintained by OpenClaw Foundation

v2026.11.6released
4 pros · 4 cons

mattpocock/skills

Small, composable agent skills for real engineering work.

Maintained by Matt Pocock (AI Hero)

4 pros · 4 cons

obra/superpowers

An agentic skills framework and software methodology that works.

Maintained by Jesse Vincent (obra)

4 pros · 4 cons

Connections

Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.

Maintained by · 1

  • shinprOrganisation

Built on · 1

Similar entries · 3

Sources

DisclosureAdded by Harness Hub's automated review of public metadata; not independently tested.

  1. GitHub repo

The Harness Hub newsletter

New harness companies, projects, releases and the monthly State of Harness report, in your inbox.