Stanshy/AgentHub

One person, one software company. Manage 47 AI agents from a single Electron app — with Harness Engineering (Skills + Hooks + FileWatchers) for disciplined, traceable AI workflows.

200Stars on the repository
26Mods indexed here, across every type
4mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

dev-plan

01

Stanshy/AgentHub

Skill Claude CodeCodex

Generate a development plan with task breakdown and section 10 tracking tables.

200 +1 4mo ago A 16 tokens original MIT

gate-record

02

Stanshy/AgentHub

Skill Claude CodeCodex

Record a gate review decision in the dev plan section 10.

200 +1 4mo ago A 15 tokens original MIT

harness-audit

03

Stanshy/AgentHub

Skill Claude CodeCodex

Periodic Harness health audit based on 7 design principles.

200 +1 4mo ago A 15 tokens original MIT

knowledge-feedback

04

Stanshy/AgentHub

Skill Claude CodeCodex

Scan child projects for pitfalls and propose company standard updates.

200 +1 4mo ago A 13 tokens original MIT

pitfall-record

05

Stanshy/AgentHub

Skill Claude CodeCodex

Record a pitfall or lesson learned in the postmortem log.

200 +1 4mo ago A 17 tokens original MIT

pitfall-resolve

06

Stanshy/AgentHub

Skill Claude CodeCodex

Mark a pitfall record as resolved in the postmortem log.

200 +1 4mo ago A 18 tokens original MIT

pm-review

07

Stanshy/AgentHub

Skill Claude CodeCodex

PM reviews gate submission with 6-item checklist and recommendation.

200 +1 4mo ago A 14 tokens original MIT

pre-deploy

08

Stanshy/AgentHub

Skill Claude CodeCodex

Pre-deployment checklist for G5 submission.

200 +1 4mo ago A 12 tokens original MIT

product-diagnosis

09

Stanshy/AgentHub

Skill Claude CodeCodex

Six-question diagnostic framework for G0 pre-check — validate product direction before development starts.

200 +1 4mo ago A 21 tokens original MIT

project-kickoff

10

Stanshy/AgentHub

Skill Claude CodeCodex

Initialize new project with CLAUDE.md, .knowledge/ structure, company rules, and git.

200 +1 4mo ago A 24 tokens original MIT

review

11

Stanshy/AgentHub

Skill Claude CodeCodex

L1 internal review with auto-detection, design comparison, and Gate escalation path.

200 +1 4mo ago A 18 tokens original MIT

sop-deploy

12

Stanshy/AgentHub

Skill Claude CodeCodex

A pre-deployment checklist for checking whether a project is ready to be released to staging or production. It covers automated checks, environment settings, database changes, Docker files, and security.

200 +1 4mo ago A 26 tokens original MIT

sop-execute

13

Stanshy/AgentHub

Skill Claude CodeCodex

A step-by-step task execution workflow with required checkpoints for coding agents.

200 +1 4mo ago A 32 tokens original MIT

sop-plan

14

Stanshy/AgentHub

Skill Claude CodeCodex

A planning workflow for starting a development task by loading project plans, past incident records, and architecture notes. It then assesses complexity and breaks the work into tasks.

200 +1 4mo ago A 28 tokens original MIT

sop-review

15

Stanshy/AgentHub

Skill Claude CodeCodex

A structured code-review procedure for checking a task against project rules and acceptance criteria. It loads the task, relevant standards, and the Git changes before reviewing every required checkpoint.

200 +1 4mo ago A 29 tokens original MIT

spec-update

16

Stanshy/AgentHub

Skill Claude CodeCodex

A controlled process for updating specification documents, which describe agreed technical rules such as API behavior or data formats.

200 +1 4mo ago A 31 tokens original MIT

sprint-close

17

Stanshy/AgentHub

Skill Claude CodeCodex

Merge sprint branch to base branch, tag release, and clean up branches.

200 +1 4mo ago A 18 tokens original MIT

sprint-proposal

18

Stanshy/AgentHub

Skill Claude CodeCodex

Generate a sprint proposal document with scope, risks, and G0 checklist.

200 +1 4mo ago A 19 tokens original MIT

sprint-retro

19

Stanshy/AgentHub

Skill Claude CodeCodex

Generate sprint retrospective by analyzing section 10 data.

200 +1 4mo ago A 14 tokens original MIT

task-approve

20

Stanshy/AgentHub

Skill Claude CodeCodex

Mark a task as done after L1 review passes.

200 +1 4mo ago A 14 tokens original MIT

task-delegation

21

Stanshy/AgentHub

Skill Claude CodeCodex

Create task breakdown in dev plan section 6 and generate .tasks/ files.

200 +1 4mo ago A 20 tokens original MIT

task-dispatch

22

Stanshy/AgentHub

Skill Claude CodeCodex

Boss dispatches tasks — auto-create .tasks/ files and record in dev-plan.

200 +1 4mo ago A 20 tokens original MIT

task-done

23

Stanshy/AgentHub

Skill Claude CodeCodex

Mark a task as inreview (pending L1 review) and record in dev plan section 10.

200 +1 4mo ago A 24 tokens original MIT

task-start

24

Stanshy/AgentHub

Skill Claude CodeCodex

Mark a task as inprogress when agent begins working.

200 +1 4mo ago A 13 tokens original MIT