Eduardo-Salvador

17 mods across 1 repository, 5 stars between them.

Eduardo-Salvador/Agent-Harness-Kit

Skill Claude CodeCodex

Automatically use for every Codex implementation or independent-review dispatch. Select the neutral role, construct a minimal context packet, invoke a fresh native subagent with resolved model/reasoning, and persist adapter-owned evidence; degrade explicitly when subagents are unavailable.

5 yesterday A 56 tokens original MIT

feature-discovery

02

Eduardo-Salvador/Agent-Harness-Kit

Skill Claude CodeCodex

Automatically use when a user wants to brainstorm, explore, shape, or add a new product feature, workflow, integration, or user-facing capability and consequential product choices are not yet approved. Do not use for bugs, maintenance, tiny copy/style changes, or straightforward implementation from an approved feature…

5 yesterday A 66 tokens original MIT

frontend-screen

04

Eduardo-Salvador/Agent-Harness-Kit

Skill Claude CodeCodex

Default workflow for creating or redesigning a frontend screen, landing page, portfolio page, or responsive web section when visual direction and implementation fidelity matter.

5 yesterday A 32 tokens original MIT

parallel-dispatch

07

Eduardo-Salvador/Agent-Harness-Kit

Skill Claude CodeCodex

Automatically use when two or more graph nodes may be ready for implementation and the host may support parallel subagents or tasks. Select a safe batch, dispatch it without waiting between launches, keep capacity filled, and fan in only through declared dependencies/integration nodes.

5 yesterday A 55 tokens original MIT

project-learning

08

Eduardo-Salvador/Agent-Harness-Kit

Skill Claude CodeCodex

Activate or run project learning when the user asks to study, learn through current work, enable study mode, receive guided practice, keep learning notes, assess progress, debrief, or publish learning.

5 yesterday A 42 tokens original MIT

request-router

09

Eduardo-Salvador/Agent-Harness-Kit

Skill Claude CodeCodex

Automatically classify every request before Harness ceremony into direct-trivial, vibe, graph-only, or full-harness using deterministic rules first and AI only for genuine ambiguity.

5 yesterday A 35 tokens original MIT

test-driven-task

10

Eduardo-Salvador/Agent-Harness-Kit

Skill Claude CodeCodex

Automatically use for full-harness code behavior changes and bug fixes after task dispatch. Do not activate for eligible direct-trivial or vibe routes; otherwise enforce RED, minimum GREEN, and proportional regression.

5 yesterday A 43 tokens original MIT

writing-plans

11

Eduardo-Salvador/Agent-Harness-Kit

Skill Claude CodeCodex

Automatically use when non-trivial implementation work needs executable, spec-driven units. Do not activate for a direct-trivial presentational or static-content edit; narrowly simple engineering work still receives a compact inline spec.

5 yesterday A 45 tokens original MIT

Eduardo-Salvador/Agent-Harness-Kit

Instructions file CodexOpenCode

Instructions for Eduardo-Salvador/Agent-Harness-Kit, covering agent harness kit — operational map, request-routing gate — before all harness ceremony, direct-trivial fast path, vibe fast path and context pressure and graph-only tasks.

5 yesterday A 4,400 tokens original MIT

Eduardo-Salvador/Agent-Harness-Kit

Instructions file

Instructions for Eduardo-Salvador/Agent-Harness-Kit, a project described as: An installable harness for Codex and Claude Code that gives coding agents durable context, scoped task graphs, bounded execution, and a clear path from idea to verified delivery.

5 yesterday A 339 tokens original MIT