loomcycle: Instructions file for Claude Code

CLAUDE.md

loomcycle CLAUDE.md is an instructions file for Claude Code from denn-gubsky/loomcycle. It costs 13,063 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for loomcycle, a Go service that runs AI tool-use loops and connects applications to several AI providers.

In plain words
What is it for?
Use them when changing loomcycle or reviewing its code, especially its provider integrations, agent handling, service interfaces, and tenant isolation.
Why use it?
They give the coding agent the project background, development process, coding discipline, and security rules it must follow in every session.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is denn-gubsky/loomcycle's own configuration. It tells Claude Code how to work on loomcycle itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything loomcycle configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/denn/workspace/jobs_search_agent.

Reuse

Borrowing it

Nothing to install: this file belongs to denn-gubsky/loomcycle. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/denn-gubsky/loomcycle/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/denn-gubsky/loomcycle

Made for: Claude Code.

Wrote 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.

agentmods badge for loomcycle CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/denn-gubsky/loomcycle/claude-md.svg)](https://agentmods.dev/instructions/denn-gubsky/loomcycle/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/denn-gubsky/loomcycle/claude-md"><img src="https://agentmods.dev/badge/instructions/denn-gubsky/loomcycle/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 13,063 This file is loaded in full into every session.
When invoked 13,063 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original 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 5.1 $0.13063 $0.13063
Opus 5 $0.06531 $0.06531
Sonnet 5 $0.02613 $0.02613
Haiku 4.5 $0.01306 $0.01306

Measured 3d ago against content hash 04a5f45386c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

loomcycle CLAUDE.md scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

8. **Manual tests** — `go build -o bin/loomcycle ./cmd/loomcycle && ./bin/loomcycle --config <yaml>`, then `curl` the affected endpoint. For loop / provider / tool changes, run an actual end-to-end agent run against a re
CLAUDE.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — loomcycle project guide

This file is loaded by Claude Code on every session in this repo. Read it cold; act from it without re-discovery.

Project context

loomcycle is a high-load agentic runtime: one Go binary that owns the LLM tool-use loop end-to-end (model → tool_use → tool_result → model), runs as a sidecar, and is consumed by application servers over HTTP+SSE / gRPC / MCP / a TS adapter. Multi-provider (Anthropic, OpenAI, DeepSeek, Gemini, Ollama; + a synthetic code-js provider). Multi-tenant (per-principal tokens, tenant-isolated state + definition planes). Multi-agent (parent agents spawn sub-agents via the built-in Agent tool). Apache-2.0.

It exists because vendor SDKs (@anthropic-ai/claude-agent-sdk, OpenAI Agents SDK) bundle a binary, hide the loop, and lock you into one provider. Spawning that binary per call is 20–30 s cold-start, leaks memory under load, and pins a fleet to one model. loomcycle replaces the SDK with a pure HTTP-only loop, exposes native cache-control where the provider supports it, and stays single-tenant-friendly while being shaped to grow into multi-tenant production.

Where it sits in the stack:

   App / n8n / LangChain  ──HTTP+SSE · gRPC · MCP · TS──▶  loomcycle (this repo)  ──HTTP──▶  Anthropic / OpenAI / DeepSeek / Gemini / Ollama  (+ code-js, mock)
                                  │
                                  ├─ built-in tools (Read/Write/Edit/Grep/Glob/NotebookEdit/HTTP/WebFetch/WebSearch/Bash/Agent/Skill/Memory/Recall/Channel/AgentDef/SkillDef/Evaluation/Interruption/Context)
                                  ├─ substrate Defs (Agent/Skill/MCPServer/Schedule/Webhook/MemoryBackend/A2A — runtime-mutable, tenant-scoped)
                                  ├─ MCP servers (stdio pool + HTTP)   ·   MCP server surface (`loomcycle mcp [--upstream]`)
                                  ├─ triggers: Scheduler · inbound Webhooks · A2A peers
                                  └─ LLM Gateway (OpenAI-compatible) · LocalAPI gateway (OpenAPI → tools)

Read the full file on GitHub · 134 lines

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. 3d ago Changed · +4 tokens per session 04a5f45386c3
  2. 7d ago First seen · 134 lines · 13,059 tokens per session scan A f9b6bc7e311b

Subscribe to this mod's changes

loomcycle CLAUDE.md is an instructions file published in the GitHub repository denn-gubsky/loomcycle (13 stars, last pushed 4d ago), licensed Apache-2.0. It adds 13,063 tokens to every session, about $0.0653 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens