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/catkamakura/lightnovel-immersive-reader/agents-mdgit clone --depth 1 https://github.com/Catkamakura/lightnovel-immersive-readerWrote 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/catkamakura/lightnovel-immersive-reader/agents-md)<a href="https://agentmods.dev/instructions/catkamakura/lightnovel-immersive-reader/agents-md"><img src="https://agentmods.dev/badge/instructions/catkamakura/lightnovel-immersive-reader/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 | $0.03376 | $0.03376 |
| Opus 5 | $0.01688 | $0.01688 |
| Sonnet 5 | $0.00675 | $0.00675 |
| Haiku 4.5 | $0.00338 | $0.00338 |
Grade A, and why
lightnovel-immersive-reader 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://127.0.0.1:8788/api/health How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Orientation for an AI coding agent (and for Claude Code / Cursor). Start here.
lightnovel-immersive-reader is a two-part personal-reading tool for www.lightnovel.fun. Part 1 is a single-file Tampermonkey userscript (lightnovel-immersive-reader.user.js, ~1900 lines of vanilla JS in one IIFE) that injects a clean, Google-Docs-style immersive reader into the live site without replacing it — it renders into a Shadow-DOM overlay under host lkir-host and reads the site's own JSON web API same-origin (POST /proxy/api/...). It supports continuous-scroll single articles and seamless continuous-scroll web novels (a windowed chapter flow with background prefetch and lazy content-visibility chunk rendering; a settings toggle falls back to the paged one-chapter-per-page reader), auto/manual chapterization, per-chapter bookmarks, a minimap, themes, account-scoped resume, and one-click EPUB/TXT export or send-to-Calibre. Part 2 is calibre-bridge/, an optional FastAPI companion the reader POSTs an EPUB to; it enriches the EPUB's OPF metadata and drops the file into a Calibre-Web-Automated (CWA) ingest folder (import-only — no progress/bookmark sync, no kosync).
Project map
| Path | What it is |
|---|---|
lightnovel-immersive-reader.user.js |
The whole reader. One IIFE: config/themes → API envelope → helpers (stripTags/esc/norm) → chapterize/buildEpub → render (stream / paged series / seamless flow renderFlow, outline, minimap) → metadata (extractCredits/extractMetaLLM/buildLibMeta) → resume/progress → boot (lkir-host shadow root, SPA route watcher). |
package.json |
npm metadata + verify* scripts. The userscript header @version (currently 2.0.0) is the source of truth for the reader's version. |
verify/verify-userscript.mjs |
Playwright smoke test: injects the script (with a GM_xmlhttpRequest shim) into the live site, opens the reader, asserts UI. |
verify/verify-webnovel.mjs |
Playwright checks for the web-novel (series) mode: seamless flow (append/prepend/leap/bookmarks/minimap) + the paged fallback toggle. |
verify/verify-lib.mjs |
Playwright checks for the send-to-library flow. |
calibre-bridge/ |
Optional FastAPI companion (uv + Docker). |
calibre-bridge/bridge/main.py |
FastAPI app + endpoints (/api/health, /api/import, /api/lookup, /api/books), custom CORS/PNA middleware, bearer-token auth. |
calibre-bridge/bridge/epub_meta.py |
enrich_epub / enrich_opf_bytes: rewrites the EPUB's OPF (Dublin-Core + Calibre fields, MARC relator roles). |
calibre-bridge/bridge/calibre.py |
import_epub: drop into CWA ingest folder (default) or add via calibredb CLI. |
calibre-bridge/bridge/store.py |
SQLite book registry (upsert_book/list_book/get_book) for /api/lookup. |
calibre-bridge/bridge/config.py |
Env-driven Config (BRIDGE_MODE, INGEST_DIR, STATE_DB, CORS_ORIGINS, BRIDGE_TOKEN). |
calibre-bridge/tests/ |
pytest suite (OPF enrichment, store, API import/auth). |
calibre-bridge/{Dockerfile,docker-compose.yml,.env.example} |
Container scaffold that stands up CWA and the bridge together. |
calibre-bridge/README.md |
The bridge's user/operator doc (architecture, deploy modes, caveats). |
docs/ |
The English wiki: architecture, userscript reference, metadata, lk-web-api, calibre-bridge, development. |
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 · 101 lines · 3,376 tokens per session scan A ac90ceb8fc69
lightnovel-immersive-reader AGENTS.md is an instructions file published in the GitHub repository Catkamakura/lightnovel-immersive-reader (5 stars, last pushed 2mo ago), licensed MIT. It adds 3,376 tokens to every session, about $0.0169 per session on Opus 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.
Other instructions, from other repositories
Browser4 CLAUDE.md
Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
cc-websearch CLAUDE.md
Claude Code instructions for Djarvur/cc-websearch, covering project, constraints, technology stack, what not to add and conventions.
fix-quera AGENTS.md
Instructions for AlirezaKeshavarz83/fix-quera, covering agent guidance, project shape, visual style, quera page data findings and compatibility findings.
sniff AGENTS.md
AGENTS.md instructions for Aboudjem/sniff, covering agents.md: sniff, what this repo is, how an agent should use sniff, handling the playwright setup gate and finding output schema.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
sendblue-browser-use AGENTS.md
Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).