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/flukeatzerocool/holonovel/agents-mdgit clone --depth 1 https://github.com/flukeatzerocool/holonovelWrote 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/flukeatzerocool/holonovel/agents-md)<a href="https://agentmods.dev/instructions/flukeatzerocool/holonovel/agents-md"><img src="https://agentmods.dev/badge/instructions/flukeatzerocool/holonovel/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 | $0.03394 | $0.03394 |
| Opus 5 | $0.01697 | $0.01697 |
| Sonnet 5 | $0.00679 | $0.00679 |
| Haiku 4.5 | $0.00339 | $0.00339 |
Grade A, and why
holonovel 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 3d 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project overview
This repository holds the Holonovel specification — a self-contained
build specification for an MCP server that serves tabletop RPG rulesets from
Markdown sources. The canonical document is holonovel.md. This is a
specification document, not an implementation.
Spec Kit phased model
The specification follows the Spec Kit phased-artifact model: constitution
(§4 Standing Rules), specify (spec/ sources), plan and tasks
(per-increment artifacts under plans/), implement (§6 Build Process), and
converge (§6.5/§6.7). The house executable-spec conventions (gates,
traceability, golden transcript) are the quality checklist layer.
Layer map
holonovel.md Assembled specification (generated from spec/, committed)
spec/ Source files — edit here, not holonovel.md directly
├── 01-foundations.md Reading guide, mission, failure modes
├── 01a-constitution.md §4 standing rules and terminology
├── 02-requirements.md §5 requirements (the normative core)
├── 03-build.md §6 build process (includes Prepare: phase-loading hints)
├── 04-runtime.md §7 runtime conventions
├── 05-verification.md §8 verification workflows
├── 06-artifacts.md §9 artifacts and handoff
├── 07-independent.md §10 independent verification
├── 08-synthesis.md §11 optional workflows (Synthesis)
├── appendices-reference.md # Appendices heading + A, D–S (reference material)
├── appendices-fixtures.md B, C, N (golden, injection, complex fixtures)
├── appendices-licenses.md U (content licenses)
├── appendices-runbooks.md V (workflow runbooks)
└── build-phase-map.md Build-phase-to-file dependency table (per-phase loading)
File numbering follows canonical load order, not section number
(e.g., 03-build.md = third file loaded, contains §6).
README.md Project orientation; see HTML comment at top for
README design conventions
CHANGELOG.md Revision history (date-headed, bulleted)
AGENTS.md This file — AI maintainer orientation
package.json Task runner (lint, validate, typecheck)
.markdownlint.json Lint rules (120-char prose, ATX headings)
tsconfig.json TypeScript configuration
scripts/validate.ts Cross-reference checker with --traceability flag
(REQ citations, test IDs, TOC sync, heading separators,
block shape, traceability matrix, coverage completeness,
phase-map consistency; ambiguity and assumption audits
merged here)
scripts/fmea.ts REQ-level failure mode and effects skeleton
scripts/graph-deps.ts REQ dependency graph (DOT/Graphviz output)
scripts/spec-health-trends.ts Spec health metrics over revisions
scripts/lib/parse-spec.ts Shared parsers (readSpec, extractReqBodies)
scripts/lib/parse-readme.ts README structural parsers (headings, links, blockquotes)
scripts/validate-readme.ts README guardrail (structure, voice, links, comparison table)
scripts/detect-near-dupes.ts Near-duplicate paragraph detector
scripts/check-traceability.ts DECISIONS.md traceability drift check (Deferred/Waived
entries cross-referenced against registered tools/resources)
scripts/fingerprint.ts REQ-313 implementation fingerprint computation
scripts/update-server.ts Fingerprint-scoped Update workflow invoker (§6.7)
## Conventions
### Commits
Commit messages follow the CHANGELOG.md style: a date-stamped heading with
bulleted entries. Each bullet describes a coherent change group.
Push to origin: `git push origin main`.
### Prose
- Wrapped near 110 columns (markdownlint enforces a 120-char limit, tables
and code blocks excluded).
- ATX headings (`##`, `###`), not setext.
- Top-level sections separated by `---` horizontal rules.
### Spec editing
- Edit files in `spec/`. Run `npm run assemble` before committing.
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.
- 3d ago First seen · 265 lines · 3,394 tokens per session scan A 2d29327f85e2
holonovel AGENTS.md is an instructions file published in the GitHub repository flukeatzerocool/holonovel (0 stars, last pushed today), licensed MIT. It adds 3,394 tokens to every session, about $0.0170 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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.