Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/zekiriabd/SDD-Pronpx agentmods add skills/zekiriabd/sdd-pro/starting-a-new-featWrote 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/zekiriabd/sdd-pro/starting-a-new-feat)<a href="https://agentmods.dev/skills/zekiriabd/sdd-pro/starting-a-new-feat"><img src="https://agentmods.dev/badge/skills/zekiriabd/sdd-pro/starting-a-new-feat/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/zekiriabd/sdd-pro/starting-a-new-feat"><img src="https://agentmods.dev/badge/skills/zekiriabd/sdd-pro/starting-a-new-feat.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 | $0.00104 | $0.01794 |
| Opus 5 | $0.00052 | $0.00897 |
| Sonnet 5 | $0.00021 | $0.00359 |
| Haiku 4.5 | $0.00010 | $0.00179 |
Grade A, and why
starting-a-new-feat 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 9d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill — Starting a New FEAT in SDDPro
Auto-trigger : intention "nouvelle fonctionnalité" détectée. But : empêcher Claude de coder directement sans cadrage. Forcer le passage par
/feat-generate(3-6 questions élicitor).
Décision tree
Étape 1 : vérifier l'état du projet
python .sdd/python/sdd_scripts/sdd_state.py status --json
Cas selon état détecté :
| État | Action |
|---|---|
Pas de stack.md |
STOP. "Le projet n'est pas bootstrappé. Lancer python bootstrap.py ou /sdd-bootstrap d'abord." |
stack.md OK, 0 FEAT, projet ≥ moyen (estimation ≥ 3 FEATs à venir) |
Proposer Phase 0 Discovery avant /feat-generate (cf. §2 ci-dessous) |
stack.md OK, 0 FEAT, petit projet (1-2 FEATs) |
Aller direct /feat-generate <Nom> |
| ≥ 1 FEAT existante | Vérifier si la nouvelle demande est une nouvelle FEAT OU une US à ajouter à une FEAT existante (cf. §3) |
Étape 2 : Phase 0 Discovery (optionnelle mais recommandée)
Si projet moyennement complexe (≥ 3 FEATs à venir, audience ≥ 2 personas), proposer au Tech Lead :
Avant de cadrer la 1ʳᵉ FEAT, veux-tu un Discovery rapide ? (10-30 min)
- /sdd-help "phase 0" pour les templates
- product-brief.template.md : sections classiques (vision, personas, KPIs, hypothèses)
- prfaq.template.md : Amazon "Working Backwards" (1 page communiqué + FAQ)
Bénéfice : éviter le scope creep en FEATs parasites.
Si oui → guider vers .sdd/templates/{product-brief,prfaq}.template.md.
Si non → aller §3.
Étape 3 : nouvelle FEAT ou US dans FEAT existante ?
Avant de spawner /feat-generate, lire les FEATs existantes pour
détecter si la demande est :
- Vraie nouvelle FEAT : nouveau domaine métier, nouveaux acteurs,
≥ 3 User Stories prévisibles →
/feat-generate <Nom> - US dans FEAT existante : extension d'un domaine déjà cadré
(ex. "ajouter le SSO" alors que FEAT Auth existe) → ajouter une US
manuellement dans
workspace/us/{n}-{m}-{Name}.mdpuis/dev-run {n}(ou compléter la FEAT puis/us-generate {n})
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.
- 9d ago First seen · 142 lines · 104 tokens per session scan A e235072b30fa
starting-a-new-feat is a skill published in the GitHub repository zekiriabd/SDD-Pro (193 stars, last pushed 9d ago), licensed Apache-2.0. It adds 104 tokens to every session and 1,794 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…