arcvellum: Instructions file for Codex

AGENTS.md

arcvellum AGENTS.md is an instructions file for Codex, OpenCode from o-1717986918/arcvellum. It costs 737 tokens per session, scanned A, original, MIT.

A repository guide for coding agents working on a standalone literary-writing studio. It explains which part owns each job, how the product connects to agent runtimes, and what must not be added.

In plain words
What is it for?
Use it when changing the studio, its embedded writing workflow, project handling, frontend, task execution, verification, or exports.
Why use it?
It prevents agents from guessing the architecture or creating unwanted dependencies, model integrations, or hidden fallback behavior.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

This is o-1717986918/arcvellum's own configuration. It tells Codex and OpenCode how to work on arcvellum 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 arcvellum configures →

Reuse

Borrowing it

Nothing to install: this file belongs to o-1717986918/arcvellum. 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/o-1717986918/arcvellum/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/o-1717986918/arcvellum

Made for: Codex, OpenCode.

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 arcvellum AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/o-1717986918/arcvellum/agents-md/github.svg)](https://agentmods.dev/instructions/o-1717986918/arcvellum/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/o-1717986918/arcvellum/agents-md"><img src="https://agentmods.dev/badge/instructions/o-1717986918/arcvellum/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for arcvellum AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/o-1717986918/arcvellum/agents-md"><img src="https://agentmods.dev/badge/instructions/o-1717986918/arcvellum/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 737 This file is loaded in full into every session.
When invoked 737 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00737 $0.00737
Opus 5 $0.00368 $0.00368
Sonnet 5 $0.00147 $0.00147
Haiku 4.5 $0.00074 $0.00074

Measured yesterday against content hash 1fed1731bd8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

arcvellum 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 yesterday.

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.

AGENTS

This repository is a standalone Literary Engineering Studio. It embeds the workflow engine, task contracts, prompt assets, schemas, deterministic gates, project templates, and export logic required at runtime.

Product Boundary

  • The embedded engine owns literary routes, task packages, schemas, deterministic checks, promotion, canon, review, export, and release gates.
  • The Studio layer owns project lifecycle, user directions, Agent runtime discovery, isolated task workspaces, process execution, writeback, streaming observation, and the user-facing client.
  • Do not introduce a runtime dependency on literary-engineering-project-skill, LEW_CORE_REPO, or another source checkout.
  • Do not add a model-provider abstraction, API-key store, direct HTTP LLM client, or hidden fallback model call. Intelligence comes from a connected host Agent or an installed Agent runtime such as Claude Code or Codex CLI.
  • The frontend is the primary user client. New project-management or human-decision capabilities should be exposed there instead of requiring users to edit project files.

Development Entry

Do not discover architecture by searching the whole repository and editing the first matching file.

  1. Locate the owning module in docs/architecture/module-catalog.md.
  2. Follow docs/architecture/agent-interface-development-standard.md and write a Module Change Packet before editing.
  3. Import Engine behavior only through literary_engineering_studio_engine.public surfaces.
  4. Compose replaceable infrastructure only through ApplicationContainer and Studio-owned ports.
  5. Use the owning Vue feature client; components must not call the generic transport directly.

docs/architecture/module-boundaries.md contains detailed implementation history. docs/architecture/generated-module-map.md is a machine-generated ownership inventory, not a substitute for the stable public interfaces above.

Worker Constitution

  1. Obtain formal work only through embedded task-next and task-open state-machine operations.
  2. Stage only the task package, its listed reading, user-direction digest, and source_paths.
  3. Allow an Agent runtime to write only expected_outputs inside the isolated workspace.
  4. Reject unexpected file changes before importing anything.
  5. Back up an existing expected output before replacement.
  6. Import expected outputs, then call task-submit and task-complete.
  7. Treat route-audit as final evidence; Studio must not reinterpret a failed gate as success.
  8. Pause at human approval, canon apply, state apply, and release/publish approval tasks.
  9. Never enable a debug waiver or LEW_MAINTAINER_MODE.
  10. The selected external CLI instance is the main Agent for creative tasks. It must not delegate body prose to subagents.
  11. Never expose legacy embedded provider commands through Studio API, UI, or public CLI.

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. yesterday Changed · -2 tokens per session 1fed1731bd8b
  2. 8d ago First seen · 56 lines · 739 tokens per session scan A 45208267fe53

Subscribe to this mod's changes

arcvellum AGENTS.md is an instructions file published in the GitHub repository o-1717986918/arcvellum (13 stars, last pushed yesterday), licensed MIT. It adds 737 tokens to every session, about $0.0037 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 2026-08-30.

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 · 5,153 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