umbel: Instructions file for Claude Code

CLAUDE.md

umbel CLAUDE.md is an instructions file for Claude Code, Codex from jahala/umbel. It costs 3,169 tokens per session, scanned B, original, MIT.

Repository instructions for Claude Code covering umbel, a TypeScript tool that controls interactive coding-agent command lines through tmux, a terminal session manager.

In plain words
What is it for?
Use it when developing umbel or changing its command-line, agent-supervision, MCP, or workflow features.
Why use it?
It gives the coding assistant the project's architecture, technology choices, and rules for making changes safely.

Instructions file for Claude CodeCodex

Written for Codex and Claude Code: reads ~/.codex or $CODEX_HOME, but also the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is jahala/umbel's own configuration. It tells Claude Code and Codex how to work on umbel 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 umbel configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jahala/umbel. 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/jahala/umbel/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jahala/umbel

Made for: Claude Code, Codex.

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 umbel CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jahala/umbel/claude-md.svg)](https://agentmods.dev/instructions/jahala/umbel/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jahala/umbel/claude-md"><img src="https://agentmods.dev/badge/instructions/jahala/umbel/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,169 This file is loaded in full into every session.
When invoked 3,169 The same file — it is already loaded in full.
Security scan B 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 $0.03169 $0.03169
Opus 5 $0.01584 $0.01584
Sonnet 5 $0.00634 $0.00634
Haiku 4.5 $0.00317 $0.00317

Measured 6d ago against content hash 391faf4eba47, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

umbel CLAUDE.md scanned grade B 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 6d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

For Gemini, the provider writes `<cwd>/.gemini/settings.json` into the worker's `cwd` (absolute path recorded in `meta.providerFiles` so `kill` cleans up). Codex instead uses a shared, umbel-managed `$CODEX_HOME` (`$UMBE
CLAUDE.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

umbel — Project Guidelines for Claude Code

What this is

umbel remote-controls the interactive claude TUI (and similar agent CLIs) over tmux. One TypeScript binary, three faces:

  • umbel -p [PROMPT] --provider {claude,codex,gemini} — drop-in for claude -p / codex -p / gemini -p, but routed through the interactive TUI (subscription-billed). Default provider: claude.
  • umbel spawn|send|wait|status|kill (also via MCP) — supervisor verbs for agent-as-supervisor orchestration. spawn --provider picks the worker; the provider is recorded in meta.json so subsequent verbs auto-route.
  • umbel run workflow.yaml — declarative pipelines with per-worker provider:.

Read docs/architecture-v3.md before writing code. It's the canonical multi-CLI design.

Positioning & design filter (full thesis: docs/positioning.md). umbel runs one unit of agent work reliably and returns a result the caller can branch on; orchestration belongs to the caller, not umbel. Apply this filter to every change: invest in the noun (the worker), not the verb (the orchestration) — a new capability must be a per-worker primitive on CLI and MCP, composable by the caller, not new workflow syntax; if it can't be that, it probably doesn't belong here. Guardrails must be enforced + external + looped (check → reject + feedback + retry → halt), never advisory. Anchor identity to the neutral worker contract, not the substrate (tmux/subscription) — per-provider adapters absorb the churn; the contract stays stable. Keep the YAML face thin.

Non-negotiable principles

  1. S.U.P.E.R. — Side effects at the edge, Uncoupled logic, Pure & total functions, Explicit data flow, Replaceable by value. Lower layers know nothing about upper layers.
  2. Test first. No fix or feature without a failing test that demonstrates the need. Fake binaries (test/fixtures/fake-{claude,codex,gemini}.sh) drive e2e — never burn real subscription budget in CI. Real-binary smoke tests live in test/smoke/{claude,codex,gemini}/ and are gated on UMBEL_SMOKE=1.
  3. No daemon. tmux is the daemon. Filesystem is the state store. Every umbel invocation is short-lived. Workers never live on the default tmux socket. adapters/tmux.ts derives a private socket from the state root (UMBEL_TMUX_SOCKET overrides) and every invocation carries -L. The default socket is shared with the user's own sessions and every other agent, so anything reaping that server — a stray tmux kill-server, a user tidying up, another agent's cleanup — takes the whole fleet with it, and does it silently: a vanished session leaves no pane and no log, indistinguishable from a worker that died on its own. That exact bug cost three agents four runs to find. Never add a bare tmux call; go through the adapter or it lands on the default socket and undoes this.
  4. Files as IPC, JSONL as truth. Hook events are file touches; chokidar is the event bus. Agent output is read from the provider's transcript file (location captured per-session from the Stop/AfterAgent hook payload), NEVER from capture-pane (which is for watching, not parsing).
  5. Throw typed errors, catch at face boundary. No Result<T,E> library. Discriminated Error subclasses in src/core/errors.ts, caught and mapped to exit codes / MCP responses at the faces layer.
  6. Single zod schema per concept. Argv parser, MCP tool schema, and YAML validation all share the same zod definitions. No three-times-defined types.

Read the full file on GitHub · 129 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. 6d ago First seen · 129 lines · 3,169 tokens per session scan B 391faf4eba47

Subscribe to this mod's changes

umbel CLAUDE.md is an instructions file published in the GitHub repository jahala/umbel (2 stars, last pushed yesterday), licensed MIT. It adds 3,169 tokens to every session, about $0.0158 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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

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

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

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

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