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 instructions/snk-devcenter/addon-studio/claude-mdgit 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 | $0.01643 | $0.01643 |
| Opus 5 | $0.00822 | $0.00822 |
| Sonnet 5 | $0.00329 | $0.00329 |
| Haiku 4.5 | $0.00164 | $0.00164 |
Grade A, and why
addon-studio CLAUDE.md 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 2d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Instruções para agentes trabalhando neste repositório (o plugin em si).
Estas regras valem para o desenvolvimento do plugin. Elas não são as regras de projetos Sankhya Addon Studio consumidores — essas vivem em
plugins/addon-studio/skills/addon-studio/assets/ADDON.md.
O que é este repo
Marketplace Claude Code (snk-devcenter) + o plugin addon-studio (skills e sub-agents para projetos Sankhya Addon Studio 2.0).
.
├── CHANGELOG.md # histórico de mudanças (alimentado por PR)
├── .claude-plugin/marketplace.json # catálogo do marketplace [versão]
├── scripts/ # instaladores e artefatos de release
├── tools/skill-trigger-audit/ # esteira de auditoria de disparo das skills
└── plugins/addon-studio/
├── .claude-plugin/plugin.json # manifest do plugin [versão]
├── hooks/ # PostToolUse de encoding + SessionStart de regras
├── agents/ # sub-agents
└── skills/<nome>/SKILL.md # 1 diretório por skill
Não há build do plugin: o entregável é markdown + JSON. O único empacotamento é scripts/build-release-artifacts.sh, que gera os instaladores e pacotes anexados à GitHub Release. Validação = ler o diff, conferir os manifests (jq . <arquivo>) e, se tocar nos instaladores, rodar sh scripts/test-release-artifacts.sh.
Mexeu em description de skill ou de sub-agent? Rode a esteira de disparo antes do PR — tools/skill-trigger-audit/README.md. Ela mede se a skill dispara sem âncora no projeto e guarda o histórico em runs/; description nova sem cenário na esteira passa a ser dívida.
Versionamento — regra principal
PR não mexe em versão. Quem abre PR não decide release. Nenhum PR de conteúdo pode alterar:
plugins/addon-studio/.claude-plugin/plugin.json→version.claude-plugin/marketplace.json→plugins[].version
Esses dois só mudam no commit de corte de release, junto da tag. (A badge do README.md é dinâmica — lê a última release pela API do shields.io, não precisa de bump.) Consequência prática: subject de commit e título de PR não carregam (vX.Y.Z) — o histórico antigo faz isso, é legado, não replicar.
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.
- 2d ago First seen · 83 lines · 1,643 tokens per session scan A 49f55e3ff162
addon-studio CLAUDE.md is an instructions file published in the GitHub repository snk-devcenter/addon-studio (5 stars, last pushed 2d ago), licensed MIT. It adds 1,643 tokens to every session, about $0.0082 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 instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.