easyinplay/harnessed

AI coding harness composition orchestrator — manifest-described upstreams, composition skill workflows. Apache-2.0.

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

2Stars on the repository
30Mods indexed here, across every type
3d agoLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown

karpathy-baseline

01

easyinplay/harnessed

Skill Claude CodeCodex

ALWAYS apply Karpathy 4 心法 baseline to every coding decision: Think Before Coding / Simplicity First (YAGNI) / Surgical Changes / Goal-Driven Execution. Cross-cutting always-on heuristics — applies to ALL coding tasks regardless of language, framework, or phase. Source: andrej-karpathy-skills (forrestchang, MIT) …

not rated 2 3d ago A 83 tokens original Apache-2.0

easyinplay/harnessed

Skill Claude Code

A placeholder phase in a feature-planning workflow that returns a fixed mock result. A mock result is simulated output used to test whether the surrounding workflow moves between phases correctly.

not rated 2 3d ago A 40 tokens original Apache-2.0

easyinplay/harnessed

Skill Claude Code

A planning workflow stub that returns a simulated approval decision for a feature plan.

not rated 2 3d ago A 33 tokens original Apache-2.0

easyinplay/harnessed

Skill Claude Code

A mock discussion step for a feature-planning workflow. It currently returns an approved test result instead of holding a real discussion.

not rated 2 3d ago A 35 tokens original Apache-2.0

easyinplay/harnessed

Skill Claude Code

A mock step that saves a feature plan to Markdown files. It currently returns an approved test result instead of performing real file persistence.

not rated 2 3d ago A 37 tokens original Apache-2.0

plan-feature-plan

06

easyinplay/harnessed

Skill Claude Code

A mock planning step for deciding how a new feature should be built. It currently returns an approved test result instead of performing real planning.

not rated 2 3d ago A 34 tokens original Apache-2.0

auto

07

easyinplay/harnessed

Skill Claude Code

A one-command workflow that runs a feature from initial research, discussion, and planning through task breakdown, verification, and retrospective. It may research first when the request is unclear.

not rated 2 changed 25d ago A 221 tokens original Apache-2.0

discuss-phase

08

easyinplay/harnessed

Skill Claude Code

A two-step workflow for clarifying a software project phase when important implementation choices or connections between phases are unclear, then saving the findings to files.

not rated 2 changed 25d ago A 144 tokens original Apache-2.0

discuss-strategic

09

easyinplay/harnessed

Skill Claude Code

A planning workflow for deciding whether a new feature, milestone, or product direction should go ahead. It uses structured discussion and saves the resulting findings in a file.

not rated 2 changed 25d ago A 147 tokens original Apache-2.0

discuss-subtask

10

easyinplay/harnessed

Skill Claude Code

A discussion workflow for difficult or unclear coding subtasks. It develops at least two possible approaches and can optionally use document review or questioning tools.

not rated 2 changed 25d ago A 133 tokens original Apache-2.0

plan-architecture

11

easyinplay/harnessed

Skill Claude Code

A one-step review workflow for complex software architecture, meaning designs involving several modules, new core abstractions, scaling concerns, or migration risk.

not rated 2 changed 25d ago A 131 tokens original Apache-2.0

research

12

easyinplay/harnessed

Skill Claude Code

A multi-source research workflow that searches the web and combines the results into one discussion summary. It can route searches to tools suited to keywords, descriptive or academic queries, current news, and crawling whole websites.

not rated 2 changed 25d ago A 134 tokens original Apache-2.0

retro

13

easyinplay/harnessed

Skill Claude Code

A retrospective workflow for reviewing a finished project or milestone. It records lessons, decisions, and follow-up points in `RETROSPECTIVE.md`.

not rated 2 changed 25d ago A 191 tokens original Apache-2.0

ship-preflight

14

easyinplay/harnessed

Skill Claude Code

Stage ⑤.a Ship sub — release-preflight gate. Runs harnessed release-preflight (read-only: CHANGELOG [Unreleased] non-empty + version + git-clean + tag-absent). A failing gate blocks shipping. Nothing is pushed/published/tagged here.

not rated 2 changed 25d ago A 62 tokens original Apache-2.0

task-clarify

15

easyinplay/harnessed

Skill Claude Code

A workflow that clarifies an unclear coding subtask through brainstorming, with an optional document-based review when the specification is ambiguous.

not rated 2 changed 25d ago A 180 tokens original Apache-2.0

task-code

16

easyinplay/harnessed

Skill Claude Code

A two-phase workflow for breaking coding work into tracked subtasks and progress records. It applies rules from the project's CLAUDE.md file, which is a set of instructions for the coding assistant.

not rated 2 changed 25d ago A 160 tokens original Apache-2.0

task-deliver

17

easyinplay/harnessed

Skill Claude Code

A two-step delivery workflow for completing a subtask. It checks for the exact word “COMPLETE,” then records progress in a progress.md file.

not rated 2 changed 25d ago A 209 tokens original Apache-2.0

verify-code-review

18

easyinplay/harnessed

Skill Claude Code

A code-review workflow that sends a change to several independent reviewers at the same time. The reviewers work in separate contexts and return their findings to the main review.

not rated 2 changed 25d ago A 125 tokens original Apache-2.0

verify-design

19

easyinplay/harnessed

Skill Claude Code

A conditional design-review workflow for websites and other user interfaces. It checks design-system consistency, page structure, and visual polish when the interface has changed.

not rated 2 changed 25d ago A 132 tokens original Apache-2.0

verify-eval-review

20

easyinplay/harnessed

Skill Claude Code

A conditional review workflow for checking whether an AI feature has enough evaluation coverage. It compares the implementation with the planned evaluation areas and records each one as covered, partly covered, or missing in EVAL-REVIEW.md.

not rated 2 changed 25d ago A 116 tokens original Apache-2.0

verify-multispec

21

easyinplay/harnessed

Skill Claude Code

A verification workflow for major releases or large code refactors. It uses four specialist teammates to review the change, question each other’s findings, and then shut down cleanly.

not rated 2 changed 25d ago A 196 tokens original Apache-2.0

verify-paranoid

22

easyinplay/harnessed

Skill Claude Code

A conditional review workflow for critical modules before a pull request, which is a proposed code change awaiting review. It uses a strict senior-engineer review for important code and skips ordinary modules.

not rated 2 changed 25d ago A 131 tokens original Apache-2.0

verify-progress

23

easyinplay/harnessed

Skill Claude Code

A three-step verification workflow that first checks whether the result meets user-acceptance criteria, then synchronizes project status, and finally updates progress.md. User-acceptance criteria are checks describing what the finished work must do.

not rated 2 changed 25d ago A 156 tokens original Apache-2.0

verify-qa

24

easyinplay/harnessed

Skill Claude Code

A conditional end-to-end quality-assurance workflow for changes to a user interface. End-to-end testing checks a feature through the whole user path, often in a real browser, and this workflow also includes performance and accessibility checks.

not rated 2 changed 25d ago A 131 tokens original Apache-2.0

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: