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.
npx agentmods add instructions/naoray/scribe/agents-mdgit clone --depth 1 https://github.com/Naoray/scribeWhat 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.
| Model | Per session | Once 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 |
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.
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 ./cmdis a good focused pass for command and sync changes.go run ./cmd/scribe --helpruns the CLI locally.go run ./cmd/scribe list --jsonis 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.
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.
- 2d ago First seen · 30 lines · 486 tokens per session scan A d72464f80915
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.
Other instructions, from other repositories
dsh-TUI AGENTS.md
AGENTS.md instructions for ccch1mneyyy/dsh-TUI, covering agents.md, 仓库布局, 命令, 上游边界与契约 and 约定与红线.
golembot CLAUDE.md
Instructions for 0xranx/golembot, covering golembot — project conventions for claude code, architecture hard constraints, things you must never do, interface change rules and file responsibility boundaries.
sortie copilot-instructions.md
Instructions for sortie-ai/sortie, covering sortie coding & review standards, 1. layered imports (downward only; violation is critical), 2. concurrency safety, 3. workspace path safety (critical: security boundary) and 4. persistence (sqlite).
copperhead CLAUDE.md
Instructions for copperheadhq/copperhead, covering claude.md, what this repo is, sources of truth, workflow (openspec) and architecture (per spec.md §2).
pi-ask AGENTS.md
Instructions for eko24ive/pi-ask, covering agents.md, project scope, project goals, tech stack and commands.
amp-acp AGENTS.md
Instructions for tao12345666333/amp-acp, covering agents.md, commands, architecture and code style.