gentle-ai-bench

gentle-ai-bench is a skill for Claude Code, Codex from Gentleman-Programming/gentle-ai. It costs 49 tokens per session (694 once invoked), scanned A, original, MIT.

A guide and validation rulebook for creating and testing journeys in gentle-ai-bench, a benchmark that drives a product through defined user scenarios.

In plain words
What is it for?
Use it when changing the benchmark corpus, adding a journey, changing behavior a journey tests, or investigating related CI failures.
Why use it?
It prevents false confidence from a passing declaration-only test and helps ensure journeys are unique, correctly configured, and actually executed like the CI checks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when changing the benchmark corpus, adding a journey, changing behavior a journey tests, or investigating related CI failures.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gentleman-programming/gentle-ai/gentle-ai-bench
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.

Gentleman-Programming/gentle-ai · 6,594 stars · on GitHub · gentle-ai.gentlemanprogramming.com

Install

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.

Any agent
npx skills add Gentleman-Programming/gentle-ai --skill gentle-ai-bench
Clone the repo
git clone --depth 1 https://github.com/Gentleman-Programming/gentle-ai

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for gentle-ai-bench

README.md
[![agentmods](https://agentmods.dev/badge/skills/gentleman-programming/gentle-ai/gentle-ai-bench/github.svg)](https://agentmods.dev/skills/gentleman-programming/gentle-ai/gentle-ai-bench)
Your own site
<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.

agentmods 80×15 button for gentle-ai-bench

Your own site · 80×15
<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>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 694 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.00694
Opus 5 $0.00024 $0.00347
Sonnet 5 $0.00010 $0.00139
Haiku 4.5 $0.00005 $0.00069

Measured 11d ago against content hash 49ac672887b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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 11d 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.

internal/assets/skills/gentle-ai-bench/SKILL.md · 36 lines

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 ./bench validates 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 green go test ./bench claims nothing about execution.
  • Reproduce CI, do not guess invocations: read the Unit Tests step in .github/workflows/ci.yml and copy its exact build and gentle-ai-bench run --binary ... commands. Use --only <journey-id> to drive one journey.
  • Journey IDs are unique across every journeys_*.go file. 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) or reviewUntouched (its subject IS the switch, or it has nothing to do with reviews). The declaration is mandatory; validateCorpus fails the run without it. Never let a journey inherit the product's default: reviews are opt-in, and a journey that assumed otherwise measures a review-refused flow while still reporting completed.
  • Every execute transition 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_end prints n/a unless the run actually measured one. Never fabricate a value to move the column.
  • A by_design exemption 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_*.go file when the shared ones are owned by open PRs; bump the core journey-count pin in the same change.

Read the full file on GitHub · 36 lines

Changes

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.

  1. 11d ago First seen · 36 lines · 49 tokens per session scan A 49ac672887b4

Subscribe to this mod's changes

gentle-ai-bench is a skill published in the GitHub repository Gentleman-Programming/gentle-ai (6,594 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 694 once invoked, about $0.0002 per session on Opus 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.