What is GhostWriterFramework AGENTS.md?

A set of instructions for AI agents working on the Narrarium book-writing framework, where the repository is the source of truth for story facts and structure.

Creating and updating characters, places, factions, items, secrets, timeline events, chapters, plot summaries, and release notes in a Narrarium project.

It reduces invented or contradictory story details by requiring agents to search existing canon and follow the project's update and versioning rules.

How KeyserDSoze/GhostWriterFramework configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to KeyserDSoze/GhostWriterFramework. 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/KeyserDSoze/GhostWriterFramework/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/KeyserDSoze/GhostWriterFramework

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/keyserdsoze/ghostwriterframework/agents-md/github.svg)](https://agentmods.dev/instructions/keyserdsoze/ghostwriterframework/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/keyserdsoze/ghostwriterframework/agents-md"><img src="https://agentmods.dev/badge/instructions/keyserdsoze/ghostwriterframework/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/keyserdsoze/ghostwriterframework/agents-md"><img src="https://agentmods.dev/badge/instructions/keyserdsoze/ghostwriterframework/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 960 This file is loaded in full into every session.

When invoked 960 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.

Model	Per session	Once invoked
Fable 5.1	$0.00960	$0.00960
Opus 5.5	$0.00384	$0.00384
Sonnet 5.5	$0.00192	$0.00192
Haiku 4.5	$0.00096	$0.00096

Measured 2mo ago against content hash 1539d9660b08, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

GhostWriterFramework 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 2mo 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 · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Narrarium Agent Rules

Use Narrarium as a book-writing framework where the repository is the source of truth.

Default workflow

Search canon before inventing new facts.
Prefer Narrarium MCP tools over ad-hoc filesystem edits when creating or updating book structure.
Use rich creation tools for major canon files:
- create_character
- create_location
- create_faction
- create_item
- create_secret
- create_timeline_event
If the brief is incomplete, start a guided flow with:
- start_wizard
- wizard_answer
- wizard_finalize
After significant structural changes, refresh maintenance files:
- sync_plot
- sync_resume or sync_all_resumes
- evaluate_chapter or evaluate_book

Narrarium MCP already auto-refreshes plot.md and the resume files after final chapter or paragraph mutations. Evaluations remain manual unless explicitly requested.

Versioning and patch notes

Every application change that is committed and pushed must bump src/narrarium-site/package.json and the root lockfile version according to the repository release workflow.
Before the version bump is committed, add a matching entry to src/narrarium-site/src/content/patch-notes.json.
Every patch-note entry must contain a title, summary, and non-empty change list in both English (en) and Italian (it).
Patch notes must describe user-visible behavior and navigation, not only internal implementation details.
Never commit or push a Narrarium site version without a matching bilingual patch note. npm run bms:build enforces this rule.
After each versioned commit, push main and monitor the Deploy Narrarium Site GitHub Actions workflow until completion, unless the user explicitly requests otherwise.

Canon discipline

Do not duplicate canon if the fact already exists in another markdown file.
Keep structured facts in frontmatter and prose in markdown body.
In chapter and scene prose, write character, item, location, faction, secret, and timeline-event names as plain text. Do not insert markdown links to canon files or reader routes; the reader will link visible canon mentions.
Do not reveal a secret before its known_from or reveal_in threshold.
Treat guidelines/, drafts/, plot.md, conversations/, resumes/, evaluations/, and secrets/ as first-class context, not optional notes.

Read the full file on GitHub · 73 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.

2mo ago First seen · 73 lines · 960 tokens per session scan A 1539d9660b08

Subscribe to this mod's changes

GhostWriterFramework AGENTS.md is an instructions file published in the GitHub repository KeyserDSoze/GhostWriterFramework (0 stars, last pushed 2mo ago), licensed MIT. It adds 960 tokens to every session, about $0.0038 per session on Opus 5.5. 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.

Writing and docs

GhostWriterFramework AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
GhostWriterFramework AGENTS.mdKeyserDSoze/GhostWriterFramework	Instructions file	0	2mo ago	MIT	A	960	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

GhostWriterFramework: Instructions file for Codex