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 sdd-onboardgit 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/sdd-onboard)<a href="https://agentmods.dev/skills/gentleman-programming/gentle-ai/sdd-onboard"><img src="https://agentmods.dev/badge/skills/gentleman-programming/gentle-ai/sdd-onboard/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/sdd-onboard"><img src="https://agentmods.dev/badge/skills/gentleman-programming/gentle-ai/sdd-onboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 225 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00031 | $0.01863 |
| Opus 5 | $0.00015 | $0.00932 |
| Sonnet 5 | $0.00006 | $0.00373 |
| Haiku 4.5 | $0.00003 | $0.00186 |
Grade B, and why
sdd-onboard scanned grade B with 1 finding 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 10d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- Keep each phase narration SHORT — 1-3 sentences. Teach, don't lecture. How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ORCHESTRATOR NOTE: This skill is designed to be executed INLINE by the orchestrator. It is an interactive walkthrough — no sub-agent delegation needed.
Executor Override
If you ARE the sdd-onboard sub-agent (NOT the orchestrator), the gate above does NOT apply to you. Continue with the phase work below. Do NOT delegate. Do NOT call the Skill tool. You are the executor — execute.
Language Domain Contract
Generated technical artifacts default to English. Do not inherit the user's conversational language or the active persona's regional voice for SDD artifacts unless the user explicitly requests that artifact language or the project convention requires it.
If technical artifacts are explicitly requested in another language, use a neutral/professional register unless the user explicitly requests a different tone or regional variant.
Public/contextual comments follow the target context language by default. Explicit user language or tone overrides win; otherwise use a neutral/professional register unless the target context clearly calls for another tone or regional variant.
Purpose
You are a sub-agent responsible for ONBOARDING. You guide the user through a complete SDD cycle — from exploration to archive — using their actual codebase. This is a real change with real artifacts, not a toy example. The goal is to teach by doing.
What You Receive
From the orchestrator:
- Artifact store mode (
engram | openspec | hybrid | none) - Optional: a suggested improvement or area to focus on
What to Do
Phase 1: Welcome and Codebase Analysis
Greet the user and explain what's about to happen:
"Welcome to SDD! I'll walk you through a complete cycle using your actual codebase.
We'll find something small to improve, build all the artifacts, implement it,
and archive it. Each step I'll explain what we're doing and why.
Let me scan your codebase for opportunities..."
Then scan the codebase for a real, small improvement opportunity:
Criteria for a good onboarding change:
├── Small scope — completable in one session (30-60 min)
├── Low risk — no breaking changes, no data migrations
├── Real value — something genuinely useful, not a toy
├── Spec-worthy — has at least 1 clear requirement and 2 scenarios
└── Examples:
├── Missing input validation on a form or API endpoint
├── Inconsistent error messages in an auth flow
├── A utility function that could be extracted and reused
├── Missing loading/error state in an async component
└── A TODO or FIXME comment in the code with clear intent
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.
- 10d ago First seen · 232 lines · 31 tokens per session scan B 5fa7ed85bf88
sdd-onboard is a skill published in the GitHub repository Gentleman-Programming/gentle-ai (6,475 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 1,863 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ijfw-review
Use when the user asks for a review of any artifact -- code diff, PR, book chapter, campaign brief, landing-page copy, or design tokens. Trigger: review, code review, review this, PR review, review my X, review chapter, review brief, review page, /ijfw-review.
ijfw-cross-audit
Generate a cross-platform multi-model audit (Trident) on a diff, brief, or artifact. Trigger: 'cross audit', 'Trident', 'second opinion', 'check with other models', 'check with other AIs', 'cross-check this', 'get another perspective', /cross-audit.
requirements-authoring-flow
Workflow for authoring requirements and specifications: drafting, review, validation, etc.
ijfw-receiving-review
Reply to code review without blind agreement or performative pushback. Use when you have received feedback, need to address review, respond to review, handle review comments, or PR comments came back. Trigger: received feedback, address review, respond to review, review comments to handle, PR comments came back…
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.