scribe AGENTS.md

Repository instructions for Scribe, a Go command-line application with a terminal user interface. They describe its folders, build and test commands, coding style, and testing practices.

In plain words
What is it for?
They help develop Scribe’s commands and internal packages, build the application, run focused or complete tests, check formatting, and perform command-line smoke tests.
Why use it?
They give contributors a shared way to organize code, format it, run checks, and avoid breaking command-line or synchronization features.

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/naoray/scribe/agents-md
Clone the repo
git clone --depth 1 https://github.com/Naoray/scribe

Made for: Codex, OpenCode.

Per session 486 This file is loaded in full into every session.
When invoked 486 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 $0.00486 $0.00486
Opus 5 $0.00243 $0.00243
Sonnet 5 $0.00097 $0.00097
Haiku 4.5 $0.00049 $0.00049

Measured 2d ago against content hash d72464f80915, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scribe 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 · 30 lines

How it starts

The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

cmd/ contains CLI entrypoints and Bubble Tea TUIs, including the main binary at cmd/scribe. Core application logic lives under internal/, split by concern such as internal/workflow, internal/sync, internal/state, internal/tools, and internal/provider. User-facing docs and design notes live in docs/. Sample or local agent assets may exist under agents/, but production code should stay in cmd/ or internal/.

Build, Test, and Development Commands

  • go build ./... builds all packages and catches compile-time regressions.
  • go test ./... runs the full test suite.
  • go test ./internal/workflow ./internal/sync ./cmd is a good focused pass for command and sync changes.
  • go run ./cmd/scribe --help runs the CLI locally.
  • go run ./cmd/scribe list --json is a quick smoke test for non-TTY output.

Coding Style & Naming Conventions

Use standard Go formatting and keep code gofmt-clean. Prefer small functions, explicit error handling, and package-local helpers over cross-package shortcuts. Keep package names lowercase and file names descriptive, for example list_tui.go or syncer.go. Cobra commands should follow the existing newXCommand and runX pattern. Tests should sit next to the code they cover.

Testing Guidelines

Write table-driven Go tests where practical. Name tests with TestXxx and keep them close to the changed package. Cover behavior changes, not just happy paths; TUI and workflow regressions should include command-path tests when possible. Run go test ./... before committing.

Commit & Pull Request Guidelines

Follow the repo’s history: short imperative commit subjects such as fix: preserve tools on list TUI updates or perf: lazy-init command dependencies. Prefer focused commits over mixed refactors. PRs should explain the user-visible change, note risks or migration impact, and include terminal output or screenshots when changing TUI behavior.

Read the full file on GitHub · 30 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 · 30 lines · 486 tokens per session scan A d72464f80915

Subscribe to this mod's changes

scribe AGENTS.md is an instructions file published in the GitHub repository Naoray/scribe (5 stars, last pushed 2mo ago), licensed MIT. It adds 486 tokens to every session, about $0.0024 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.