raunen AGENTS.md

Repository instructions for raunen, a Go terminal program that lets local language models work through a text interface.

In plain words
What is it for?
Use them when changing the Go application, terminal interface, agent loop, provider connection, tools, or Agent Client Protocol transport.
Why use it?
They define the project's module boundaries, required checks, formatting rules, and limits on dependencies so the small standalone program stays maintainable.

Instructions file for CodexOpenCode

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 instructions/devjasha/raunen/agents-md
Clone the repo
git clone --depth 1 https://github.com/devjasha/raunen

Made for: Codex, OpenCode.

Per session 697 This file is loaded in full into every session.
When invoked 697 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00697 $0.00697
Opus 5 $0.00349 $0.00349
Sonnet 5 $0.00139 $0.00139
Haiku 4.5 $0.00070 $0.00070

Measured 2d ago against content hash 3588bfd6c1e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

raunen AGENTS.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.

AGENTS.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

raunen

A terminal agent for local LLMs. One Go binary, no runtime, no server. Go 1.25 or newer; the only dependencies are Bubble Tea and Lip Gloss.

Working here

  • go build ./... && go test ./... before proposing a change. Both are fast.
  • gofmt is not optional; go vet ./... should stay silent.
  • No new third-party dependencies without saying why. The binary being small and self-contained is a feature, not an accident.

Layout

  • main.go — flags, config, wiring, and the one-shot path
  • internal/agent — the tool-use loop. Presentation-free: it emits typed Events and knows nothing about the terminal. Keep it that way.
  • internal/ui — Bubble Tea model. Everything rendered goes through here.
  • internal/acp — Agent Client Protocol over stdio. A transport in front of agent.Agent: it must never grow behaviour the terminal does not have.
  • internal/provider — OpenAI-compatible streaming client
  • internal/tools — the built-in tools, rooted at the working directory. Every result is bounded at the registry, not in the tool: what does not fit is kept in the result store and reachable through the result handle, so an MCP tool cannot bypass the cap by being added later
  • internal/attach — loading images from a path or the clipboard, and the size and format limits. The wire form lives in provider.toWire, not on the message type: a session is saved as provider.Message too, and the endpoint's shape is not what belongs on disk
  • internal/fileset — what git considers part of the project; shared by the search tools and by @ completion, so the two cannot disagree
  • internal/permission — standing allow/deny rules. Gating lives in one place, Agent.dispatch; a tool must never decide its own permissions
  • internal/skills — SKILL.md discovery, including other agents' directories
  • internal/mcp — MCP client: stdio, HTTP and SSE transports, OAuth 2.1
  • internal/config — config, skills and MCP definitions on disk
  • web/ — the marketing and docs site, deployed separately. Not the agent.

Read the full file on GitHub · 56 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. 2d ago First seen · 56 lines · 697 tokens per session scan A 3588bfd6c1e1

Subscribe to this mod's changes

raunen AGENTS.md is an instructions file published in the GitHub repository devjasha/raunen (5 stars, last pushed 11d ago), licensed MIT. It adds 697 tokens to every session, about $0.0035 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.