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.
Borrowing it
Nothing to install: this file belongs to Gentleman-Programming/gentle-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Gentleman-Programming/gentle-ai/main/AGENTS.mdgit clone --depth 1 https://github.com/Gentleman-Programming/gentle-aiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/gentleman-programming/gentle-ai/agents-md)<a href="https://agentmods.dev/instructions/gentleman-programming/gentle-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/gentleman-programming/gentle-ai/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/gentleman-programming/gentle-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/gentleman-programming/gentle-ai/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00691 | $0.00691 |
| Opus 5.5 | $0.00276 | $0.00276 |
| Sonnet 5.5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
gentle-ai AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gentle AI™ — Agent Skills Index
When working on this project, load the relevant skill(s) BEFORE writing any code.
Naming convention: gentle-ai-* skills are repo-specific workflow skills. Unprefixed skills are portable writing or work-unit skills and intentionally keep their canonical names.
How to Use
- Check the trigger column to find skills that match your current task
- Load the skill by reading the SKILL.md file at the listed path
- Follow ALL patterns and rules from the loaded skill
- Multiple skills can apply simultaneously
Skills
| Skill | Trigger | Path |
|---|---|---|
issue-creation |
When creating a GitHub issue, reporting a bug, or requesting a feature. | internal/assets/skills/issue-creation/SKILL.md |
gentle-ai-branch-pr |
When creating a pull request, opening a PR, or preparing changes for review. | skills/branch-pr/SKILL.md |
gentle-ai-chained-pr |
When a change is too large for one review, or when creating chained/stacked pull requests. | skills/chained-pr/SKILL.md |
cognitive-doc-design |
When writing docs that must reduce cognitive load for readers or reviewers. | skills/cognitive-doc-design/SKILL.md |
comment-writer |
When drafting human comments, PR feedback, issue replies, or async updates. | skills/comment-writer/SKILL.md |
work-unit-commits |
When splitting implementation work into deliverable commits or chained PRs. | skills/work-unit-commits/SKILL.md |
rdd-defect-workflow |
When RDD defects involve receipts, authority, recovery, delivery gates, or kill switches. | skills/rdd-defect-workflow/SKILL.md |
rdd-advisory-transport |
When changing reviewer transport, adapters, lens prompts/schemas, or transport capability policy. | skills/rdd-advisory-transport/SKILL.md |
issue-root-resolution |
When auditing backlog roots, proposing cluster fixes, or closing resolved/outdated issues. | skills/issue-root-resolution/SKILL.md |
systemic-issue-triage |
When triaging issues, bugs, backlogs, root causes, dead ends, or blocked users. | skills/systemic-issue-triage/SKILL.md |
gentle-ai-bench |
When touching bench/, journeys, driven mode, the journey corpus, or bench axes. |
skills/gentle-ai-bench/SKILL.md |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +1 tokens per session 9af0d3fe5db3
- 1mo ago First seen · 29 lines · 690 tokens per session scan A f47c8ae5556b
gentle-ai AGENTS.md is an instructions file published in the GitHub repository Gentleman-Programming/gentle-ai (7,940 stars, last pushed today), licensed MIT. It adds 691 tokens to every session, about $0.0028 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.