What is noveletary AGENTS.md?

Repository instructions for Noveletary, a knowledge base and MCP server that tracks facts in fiction and checks whether new writing contradicts them. It supports story branches and Japanese prose.

Use them when developing or testing Noveletary’s fact storage, contradiction checks, story branches, aliases, or MCP server.

They explain how the project protects story consistency, handles hard contradictions, and sends uncertain questions to the author instead of guessing.

How penta2himajin/noveletary configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to penta2himajin/noveletary. 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/penta2himajin/noveletary/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/penta2himajin/noveletary

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/penta2himajin/noveletary/agents-md/github.svg)](https://agentmods.dev/instructions/penta2himajin/noveletary/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/penta2himajin/noveletary/agents-md"><img src="https://agentmods.dev/badge/instructions/penta2himajin/noveletary/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/penta2himajin/noveletary/agents-md"><img src="https://agentmods.dev/badge/instructions/penta2himajin/noveletary/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,284 This file is loaded in full into every session.

When invoked 2,284 The same file — it is already loaded in full.

Security scan A 1 finding. 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	$0.02284	$0.02284
Opus 5.5	$0.00914	$0.00914
Sonnet 5.5	$0.00457	$0.00457
Haiku 4.5	$0.00228	$0.00228

Measured 2mo ago against content hash 679c442dea6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

noveletary AGENTS.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

first extraction by `kwja_extract.ensure_kwja_cache` (certifi → curl fallback), which works

AGENTS.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

noveletary

Overview

noveletary (novel + secretary) is a constraint-maintained narrative knowledge base and MCP server for checking the internal consistency of fiction, with first-class support for Japanese prose. It unifies construction (adding/updating/deleting story facts) and verification (contradiction checking) into a single constraint engine: hard, decidable contradictions (a dead character acting, a monotone ledger decreasing, a temporal cycle) gate writes at construction time; softer semantic contradictions surface as questions for the author. Story branches (parallel plot drafts) are first-class via an append-only operation log; each branch is audited independently and merged with structural conflict detection.

The design principle throughout: the knowledge base and the author are the trusted core; the LLM is a fallible translator with no authority. Unresolved questions go to the author (the ground-truth oracle), not to LLM guesswork.

Project Structure

src/noveletary/
  engine.py        # constraint engine: delegates hard checks to the template executor; affected-subgraph; alias resolution
  constraints.py   # EC-grounded constraint template executor (forbid_after_state/monotone/acyclic/release) — rules as data
  store.py         # operation log + branches + persistence (SQLite) + gated add / import / audit / merge / questions / constraints
  server.py        # MCP server (FastMCP, stdio) exposing the store as tools
  kwja_extract.py  # KWJA PAS adapter -> generic predicate-argument records (zero-anaphora-resolved); records_to_facts
  extract.py       # GiNZA fallback producing the same generic record schema (degraded: no modality/zero-anaphora)
  reconcile.py     # generic reconcile (subject,predicate axis) of LLM self-report vs mechanism records
tests/             # pytest suite; core tests run without NLP extras
docs/              # engineering docs (English): handoff protocol, i18n policy
data/              # SQLite op-log (data/narrative.db) — generated on first run, NOT committed (only data/.gitkeep tracked)

Read the full file on GitHub · 145 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 · 145 lines · 2,284 tokens per session scan A 679c442dea6c

Subscribe to this mod's changes

noveletary AGENTS.md is an instructions file published in the GitHub repository penta2himajin/noveletary (0 stars, last pushed 4mo ago), licensed MIT. It adds 2,284 tokens to every session, about $0.0091 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

noveletary AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
noveletary AGENTS.mdpenta2himajin/noveletary	Instructions file	0	4mo ago	MIT	A	2,284	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

noveletary: Instructions file for Codex