Gentleman-Programming/gentle-ai

Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Spec-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in.

About the project

Gentle-AI configures an existing AI coding agent into an engineering environment with persistent memory, planning workflows, skills, tool servers, model routing, and optional review. Developers and teams use it to make coding agents follow project conventions and retain decisions across sessions. The catalogue entries are its skills, commands, agents, and instruction.

This repository also configures its own agents. See what gentle-ai tells them →

6.5kStars on the repository
73Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

Gentleman-Programming/gentle-ai

Skill Claude CodeCodex

Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.

not rated 6.5k +222 changed 7d ago A SkillSpector: pass 57 tokens original MIT

work-unit-commits

26

Gentleman-Programming/gentle-ai

Skill Claude CodeCodex

Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.

not rated 6.5k +222 changed 6d ago A SkillSpector: pass 33 tokens original MIT

Gentleman-Programming/gentle-ai

Skill Claude CodeCodex

Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…

not rated 6.5k +222 changed 7d ago A SkillSpector: warn 106 tokens original MIT

Gentleman-Programming/gentle-ai

Skill Claude CodeCodex

Trigger: root audit, atacar la raíz, issue roots, backlog roots, mechanism map, deletion-driven fix, resolver issues de raíz, close outdated issues. Audit and resolve issue clusters by verified root cause.

not rated 6.5k +222 yesterday A SkillSpector: pass 45 tokens original MIT

Gentleman-Programming/gentle-ai

Skill Claude CodeCodex

Trigger: reviewer transport, advisory transport, review adapter, lens prompt/schema, OpenCode reviewer plugin, Codex reviewer, ReviewProviderContract. Enforce the shared Go advisory reviewer transport contract.

not rated 6.5k +222 yesterday A SkillSpector: pass 46 tokens original MIT

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: