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 agentmods add skills/snk-devcenter/addon-studio/initnpx skills add snk-devcenter/addon-studio --skill initgit clone --depth 1 https://github.com/snk-devcenter/addon-studioWhat 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 | $0.00196 | $0.01292 |
| Opus 5 | $0.00098 | $0.00646 |
| Sonnet 5 | $0.00039 | $0.00258 |
| Haiku 4.5 | $0.00020 | $0.00129 |
Grade A, and why
init 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 yesterday.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Init — Setup do projeto Sankhya para o agente
Skill instala/atualiza no projeto consumidor o docs/ADDON.md (instruções do plugin para o agente) e garante que o CLAUDE.md da raiz importe esse arquivo via @docs/ADDON.md.
Quando usar
- Primeira vez configurando o projeto pra colaboração com o agente.
- Após atualizar o plugin (
/plugin update addon-studio) — re-rodar pega a versão mais recente doADDON.md. - Dev pediu "setup", "configurar CLAUDE.md", "instalar instruções", "atualizar ADDON.md".
Pré-requisito (sanity check)
Antes de copiar nada, confirme que o projeto é mesmo Sankhya Addon Studio. Procure por br.com.sankhya.addonstudio em build.gradle ou build.gradle.kts na raiz. Se ausente, pare e alerte o dev — o ADDON.md injetaria contexto errado num projeto não-Sankhya.
grep -l "br.com.sankhya.addonstudio" build.gradle build.gradle.kts 2>/dev/null
Fluxo da skill
1. Localizar o ADDON.md canônico
O template fica no diretório assets/ da skill addon-studio (convenção Agent Skills). Use a variável de ambiente ${CLAUDE_PLUGIN_ROOT} (disponível para skills de plugin — aponta para a raiz do plugin instalado):
${CLAUDE_PLUGIN_ROOT}/skills/addon-studio/assets/ADDON.md
2. Copiar ADDON.md para docs/ no projeto
mkdir -p docs
cp "${CLAUDE_PLUGIN_ROOT}/skills/addon-studio/assets/ADDON.md" ./docs/ADDON.md
Overwrite é esperado — re-rodar a skill upgrade o arquivo pra versão mais nova. Dev nunca edita docs/ADDON.md à mão (override do projeto vai no CLAUDE.md, não aqui).
3. Garantir @docs/ADDON.md no CLAUDE.md da raiz
Claude Code suporta sintaxe de import de arquivo via @<path> no CLAUDE.md. Garanta que o CLAUDE.md da raiz contenha a linha @docs/ADDON.md.
Caso A — CLAUDE.md não existe: crie o arquivo com uma linha só, o import:
@docs/ADDON.md
Nada além disso — sem título, sem seção de customizações, sem placeholder. Regra específica do projeto entra depois, quando o dev pedir; seção vazia com placeholder vira convite pro agente preencher e duplicar o que já está documentado em outro lugar do repo.
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.
- yesterday First seen · 84 lines · 0 tokens per session scan A 25770b99f25d
init is a skill published in the GitHub repository snk-devcenter/addon-studio (5 stars, last pushed yesterday), licensed MIT. It adds 196 tokens to every session and 1,292 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…