impl

A scoped coding agent for implementation work in Go or Svelte, where tests or lint checks can verify the result. Go is a programming language, and Svelte is a web interface framework.

In plain words
What is it for?
Use it for named-file Go or Svelte changes that do not involve application wiring, data formats, API or WebSocket contracts, Matter compatibility constants, or authentication and secrets.
Why use it?
It keeps implementation tasks focused on changes that have a stated acceptance command and can be checked automatically.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/sukramj/openccu-loom/impl
Clone the repo
git clone --depth 1 https://github.com/SukramJ/openccu-loom

Made for: Claude Code.

Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 874 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00055 $0.00874
Opus 5 $0.00028 $0.00437
Sonnet 5 $0.00011 $0.00175
Haiku 4.5 $0.00006 $0.00087

Measured 2d ago against content hash fa8b1153b7fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

impl 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.

.claude/agents/impl.md · 74 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Changes

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.

  1. 2d ago First seen · 74 lines · 55 tokens per session scan A fa8b1153b7fb

Subscribe to this mod's changes

impl is an agent published in the GitHub repository SukramJ/openccu-loom (5 stars, last pushed 2d ago), with no licence file. It adds 55 tokens to every session and 874 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

domain

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

ruaan-deysel/unraid-management-agent · 0 tokens

issue-tracker

Issues and specs for this repo live as GitHub issues. Use the gh CLI for all operations.

ruaan-deysel/unraid-management-agent · 0 tokens

custom-component

Read this document before changing customcomponents/hamcptools/ or a server feature that depends on the component. The HACS component and the ha-mcp server ship through separate installation paths, so compatibility must hold in both update directions.

homeassistant-ai/ha-mcp · 0 tokens

orquestra-signer

Signs and submits Solana transactions using @orquestradev/signer-mcp. Accepts a base64-encoded wire transaction produced by orquestra-tx-builder, presents a human-readable approval summary, and signs + sends only after explicit user confirmation. Uses ONLY signer-mcp tools. Examples: Context: User has an unsigned…

berkayoztunc/orquestra · 285 tokens

orquestra-tx-builder

Builds unsigned Solana transactions using Orquestra MCP's buildinstruction tool. Requires all accounts and arguments to be fully resolved before calling. Outputs a base64-encoded wire transaction (Solana RPC standard) ready for signing. Uses ONLY Orquestra MCP tools. Examples: Context: All accounts are known, user…

berkayoztunc/orquestra · 288 tokens

orquestra-researcher

Searches Solana programs via Orquestra MCP, reads their llms.txt documentation, lists all available instructions, account types, and fetches AI analysis. Use ONLY Orquestra MCP tools — no bash, no external HTTP calls. Examples: Context: User wants to understand what a Solana program does user: "What can I do with the…

berkayoztunc/orquestra · 305 tokens