Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Organic-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in.
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 →
Gentleman-Programming/gentle-ai
Skill Claude CodeCodex needs its repo
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
Gentleman-Programming/gentle-ai
Skill Claude CodeCodex
Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.
Gentleman-Programming/gentle-ai
Skill Claude CodeCodex
Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.
Gentleman-Programming/gentle-ai
Skill Claude CodeCodex
Write warm, direct collaboration comments. Trigger: PR feedback, issue replies, reviews, Slack messages, or GitHub comments.
Gentleman-Programming/gentle-ai
Skill Claude CodeCodex
Trigger: bench, journey, journeys, driven mode, gentle-ai-bench, journey corpus, j-numbers, bench axis. Author and verify gentle-ai bench journeys; go test ./bench never proves driven execution.
Gentleman-Programming/gentle-ai
Skill Claude CodeCodex
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
Gentleman-Programming/gentle-ai
Skill Claude CodeCodex
Trigger: a mapping need, parallel units, context backstop, high-risk verify, fresh review, or multi-step debug. Delegate via delegatetask for a named reason.
Gentleman-Programming/gentle-ai
Skill Claude CodeCodex
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
Gentleman-Programming/gentle-ai
Skill Claude CodeCodex
Trigger: judgment day, dual review, adversarial review, juzgar. Run explicit blind dual review with at most two scoped fix/re-judgment rounds.
Gentleman-Programming/gentle-ai
Skill Claude CodeCodex
Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.
Gentleman-Programming/gentle-ai
Skill Claude CodeCodex
Trigger: new skills, agent instructions, documenting AI usage patterns. Create LLM-first skills with valid frontmatter.
Gentleman-Programming/gentle-ai
Skill Claude CodeCodex
Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existing LLM-first skills.
Gentleman-Programming/gentle-ai
Skill Claude CodeCodex
Trigger: update skills, skill registry, actualizar skills, after skill changes. Index available skills by trigger and path.
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.
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.
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…
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.
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.
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: