Borrowing it
Nothing to install: this file belongs to arc-mcp/arc-1. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/arc-mcp/arc-1/main/.claude/skills/create-arc1-extension/SKILL.mdgit clone --depth 1 https://github.com/arc-mcp/arc-1Wrote 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/arc-mcp/arc-1/create-arc1-extension)<a href="https://agentmods.dev/skills/arc-mcp/arc-1/create-arc1-extension"><img src="https://agentmods.dev/badge/skills/arc-mcp/arc-1/create-arc1-extension/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/arc-mcp/arc-1/create-arc1-extension"><img src="https://agentmods.dev/badge/skills/arc-mcp/arc-1/create-arc1-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00113 | $0.04020 |
| Opus 5 | $0.00056 | $0.02010 |
| Sonnet 5 | $0.00023 | $0.00804 |
| Haiku 4.5 | $0.00011 | $0.00402 |
Grade A, and why
create-arc1-extension 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create an ARC-1 extension
Guides a developer through building an ARC-1 extension — a local plugin that adds Custom_*
tools to an ARC-1 instance without forking, reusing ARC-1's authenticated SAP client, the
7-scope + allow* safety ceiling, audit, and PP. Encodes the learnings from building the framework
(PR1–PR5) and verifying it live on S/4HANA.
Ground truth — read these first, mirror them:
- User guide (point the developer here):
docs_page/extensions.md— the canonical how-to (tiers,ctx.http/ctx.run, security, CF/Docker deployment). Published at the docs site under Using ARC-1 → Extensions (Custom Tools). - Spec:
docs/research/2026-06-17-extension-framework-spec.md(v1) +extension-framework-v2-spec.md(what's deferred). - Worked sample:
arc-mcp/arc-1-extension-sample— ADT + OData reads, a manifest tool,Custom_RunClass(gated execute), an OData write (Custom_CreateSalesOrder), and a full LISA custom-ICF integration (Custom_ListLanguages/GetTranslation/SetTranslation) — all live-verified on S/4HANA (real HTTP 201/200 writes). Copy the closest tool and adapt.
v1 reality (do not get this wrong): reads are open (ctx.http.get/head). Writes (ctx.http.post/
put/delete) work only to non-ADT paths (OData/ICF) behind the opt-in SAP_ALLOW_PLUGIN_RAW_WRITES.
A console class runs via ctx.run.classRun (opt-in SAP_ALLOW_PLUGIN_EXECUTE). ADT object writes
(CLAS/DDLS/… via /sap/bc/adt/…) are always refused — those are the v2 package-aware ctx.write.
Trigger
- "add a custom tool / plugin / extension to ARC-1"
- "wrap this SAP/ADT/OData endpoint as an MCP tool"
- "build my own ARC-1 tool without forking"
- "diagnostic tool on top of ARC-1" (SM37/SLG1/gateway logs, etc.)
Step 1 — decide the path (ask, don't assume)
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 · 214 lines · 113 tokens per session scan A 0aea8c53e3c3
create-arc1-extension is a skill published in the GitHub repository arc-mcp/arc-1 (183 stars, last pushed today), licensed MIT. It adds 113 tokens to every session and 4,020 once invoked, about $0.0006 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.
Other skills, from other repositories
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
telnyx-messaging-hosted-curl
Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.
nw-stress-analysis
Advanced architecture stress analysis methodology for designing systems that survive unknown stresses. Load when --residuality flag is used or when designing high-uncertainty, mission-critical systems.