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, Organic-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.

7.8kStars on the repository

29Mods indexed here, across every type

todayLast push, which is what freshness is scored on

MITLicence, which decides whether bodies are shown

Sort Relevance Recently updated Fewest tokens Security grade Repo stars Stars this week Top rated 8 mods

jd-fix-agent

Gentleman-Programming/gentle-ai

Agent Claude Code

You are a judgment-day surgical fix agent. Execute the fix instructions provided in the delegate prompt exactly.

not rated 7.8k +149 today A 35 tokens original MIT

jd-judge-a

Gentleman-Programming/gentle-ai

Agent Claude Code

You are a judgment-day adversarial reviewer (Judge A). Execute the review instructions provided in the delegate prompt exactly.

not rated 7.8k +149 changed 11d ago A 49 tokens original MIT

jd-judge-b

Gentleman-Programming/gentle-ai

Agent Claude Code

You are a judgment-day adversarial reviewer (Judge B). Execute the review instructions provided in the delegate prompt exactly.

not rated 7.8k +149 changed 11d ago A 49 tokens copy · 100% MIT

review-readability

Gentleman-Programming/gentle-ai

Agent Claude Code

R2 Readability reviewer — naming, complexity, intention, maintainability, review size, and context clarity.

not rated 7.8k +149 changed 10d ago A 26 tokens original MIT

review-refuter

Gentleman-Programming/gentle-ai

Agent Claude Code

Detached read-only refuter for one transaction-wide batch of inferential severe findings.

not rated 7.8k +149 changed 1mo ago A 20 tokens original MIT

review-reliability

Gentleman-Programming/gentle-ai

Agent Claude Code

R3 Reliability reviewer — behavior-first tests, coverage value, edge cases, determinism, contracts, and regressions.

not rated 7.8k +149 changed 10d ago A 29 tokens original MIT

review-resilience

Gentleman-Programming/gentle-ai

Agent Claude Code

R4 Resilience reviewer — fallbacks, retry/backoff, graceful degradation, observability, load, rollback, and SLO risks.

not rated 7.8k +149 changed 10d ago A 32 tokens original MIT

review-risk

Gentleman-Programming/gentle-ai

Agent Claude Code

R1 Risk reviewer — security, privilege boundaries, data exposure, dependency risks, and merge-blocking vulnerabilities.

not rated 7.8k +149 changed 10d ago A 25 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: