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.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Gentleman-Programming/gentle-ai --skill gentle-ai-benchgit 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/skills/gentleman-programming/gentle-ai/gentle-ai-bench)<a href="https://agentmods.dev/skills/gentleman-programming/gentle-ai/gentle-ai-bench"><img src="https://agentmods.dev/badge/skills/gentleman-programming/gentle-ai/gentle-ai-bench/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/skills/gentleman-programming/gentle-ai/gentle-ai-bench"><img src="https://agentmods.dev/badge/skills/gentleman-programming/gentle-ai/gentle-ai-bench.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.00707 |
| Opus 5.5 | $0.00020 | $0.00283 |
| Sonnet 5.5 | $0.00010 | $0.00141 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
gentle-ai-bench 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Activation Contract
Load when touching bench/ in gentle-ai, adding or changing a journey, changing a product semantic a journey might pin, or diagnosing a bench failure in CI's Unit Tests job.
Hard Rules
go test ./benchvalidates corpus declarations only. It does NOT execute journeys. The only driven proof is building the harness and the product binary and running the harness against it; a greengo test ./benchclaims nothing about execution.- Reproduce CI, do not guess invocations: read the Unit Tests step in
.github/workflows/ci.ymland copy its exact build andgentle-ai-bench run --binary ...commands. Use--only <journey-id>to drive one journey. - Journey IDs are unique across every
journeys_*.gofile. The collision guard fails loudly naming both files; pick an unused ID by reading the corpus, never reuse a retired one. - Every journey declares
Review:—reviewOptedIn(the runner enables receipt-driven development globally before the first step, uncounted, and fails the journey if the switch does not come on) orreviewUntouched(its subject IS the switch, or it has nothing to do with reviews). The declaration is mandatory;validateCorpusfails the run without it. Lifecycle journeys must not depend on the product default. Reviews default to ON;reviewUntoucheddoes not imply OFF. Journeys requiring OFF must explicitly disable it, while default-mode journeys must assert ON/default with unset sources. - Every
executetransition must carry a runnable command; the dead-execute guard fails the run otherwise. - When a ratified product semantic changes, grep the corpus for journeys pinning the OLD behavior before shipping. The corpus is a second test surface beyond unit tests; a journey asserting the defect keeps the defect green.
dead_endprintsn/aunless the run actually measured one. Never fabricate a value to move the column.- A
by_designexemption costs a shape from the closed vocabulary plus a verified quote of the product's own next-action text. If the quote no longer tells the operator what to do, it is a defect wearing an exemption. - Prefer a NEW
journeys_*.gofile when the shared ones are owned by open PRs; bump the core journey-count pin in the same change.
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 e94723f36499
- 1mo ago First seen · 36 lines · 49 tokens per session scan A 49ac672887b4
gentle-ai-bench is a skill published in the GitHub repository Gentleman-Programming/gentle-ai (8,012 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 707 once invoked, about $0.0002 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 skills, from other repositories
coverage
Compute code coverage for active track or module. Targets 95%+ coverage with report and justification for uncovered lines. Complements TDD workflow.
deploy-checklist
Pre-deployment verification checklist. Generates customized checklists based on tech-stack with rollback triggers. Auto-invoked by /draft:upload.
testing-strategy
Design test strategies and test plans with coverage targets. Complements /draft:coverage which measures what this skill plans. Auto-loaded by /draft:implement before TDD.
new-track
Start a new feature or bug track. Collaborative intake process with structured questions, AI guidance, and progressive refinement before generating spec.md and plan.md. Use when the user asks to 'start a new track', 'create a feature track', 'add a bug fix track', or says 'I want to build X', 'fix the Y bug', 'plan a…
jira
Unified Jira entry point. Routes to preview (default), create, or review subcommands.
adr
Create and manage Architecture Decision Records. Documents significant technical decisions with context, alternatives, and consequences. Also supports evaluate (assess proposals) and design (system design) modes.