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/jedikim/storyai/agents-mdgit clone --depth 1 https://github.com/jedikim/storyaiWrote 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.
[](https://agentmods.dev/instructions/jedikim/storyai/agents-md)<a href="https://agentmods.dev/instructions/jedikim/storyai/agents-md"><img src="https://agentmods.dev/badge/instructions/jedikim/storyai/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00735 | $0.00735 |
| Opus 5 | $0.00367 | $0.00367 |
| Sonnet 5 | $0.00147 | $0.00147 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
storyai 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 5d 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.
What it actually says
storyai — 에이전트 지침
이 저장소는 소설 원고와 그 서사 그래프입니다. 원고는 manuscript/에 마크다운으로,
그래프는 store/story.db에 있고 storyai MCP 서버로만 접근합니다.
세션 시작 시 반드시
project(mode="current")— 현재 선택된 소설이 작업 대상인지 확인한다. 다르면project(mode="list")후project(mode="select", name="…")로 먼저 전환한다.get("story://session/latest")— 이전 세션의open_threads와next를 읽는다.check(scope="book", severity="error")— 미해결 진단을 먼저 확인한다.promises(status=["eligible"])— 회수 가능한 복선을 컨텍스트에 올린다.
이 넷을 건너뛰고 집필을 시작하지 마세요. 이전 턴이 다른 호스트였을 수 있고, 그쪽 대화 이력은 남아 있지 않습니다.
세션 종료 시 반드시
propose로 새 session/ 노드를 남깁니다. open_threads와 next를 비워두지 마세요 —
적지 않은 의도는 다음 세션에 존재하지 않는 것과 같습니다.
그래프를 다루는 규칙
- 원고 전문을 툴 결과로 받지 마세요.
outline→get(include="brief")→ 정말 필요한 하나만get(include="body")순서로 좁혀 들어갑니다. - 쓰기는 전부
propose입니다.read_set에 근거로 읽은 노드와 리비전을 반드시 담으세요. 빈read_set은 거부됩니다. locked노드(세계관 규칙)는 수정 제안할 수 없습니다. 모순을 발견하면contradicts간선을 남기고 사람에게 넘기세요.- 산문 속 이름을 임의로 고치지 마세요.
mentioned_in은 soft 간선이라 보고 대상이지 자동 편집 대상이 아닙니다. - 잘 모르겠으면
graph_schema()로 타입 체계를 확인하고, 손으로 빚은 툴로 안 풀리면query(sql)로 직접 질의하세요.
집필 규칙
- 인물의 인지 시점을 어기지 마세요. 어떤 사실을 인물이 아는지는
visible_to가 결정합니다. 모르는 사실을 발화시키면 연속성 버그입니다. - 복선은
eligible상태인 것만 회수하세요.hypothetical인 복선을 회수하면 "근거 없는 해결"로 표시됩니다. - 씬의
pre조건이 만족되지 않으면 그 씬을 쓰지 마세요. 먼저 선행 씬을 확인하세요.
금지
store/story.db를 직접 열거나 수정하지 마세요. 반드시 MCP 서버를 경유합니다.manuscript/원문을 그래프 갱신 없이 고치지 마세요. 인덱스가 어긋납니다.- 시나리오·씬 텍스트를 LLM에 넘길 때 임의로 자르지 마세요.
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.
- 5d ago First seen · 48 lines · 735 tokens per session scan A 3485df751c8b
storyai AGENTS.md is an instructions file published in the GitHub repository jedikim/storyai (0 stars, last pushed 11d ago), licensed MIT. It adds 735 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 2026-08-31.
Other instructions, from other repositories
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).
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.
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).
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.
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.
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.