Borrowing it
Nothing to install: this file belongs to Muvon/octoweb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Muvon/octoweb/master/AGENTS.mdgit clone --depth 1 https://github.com/Muvon/octowebWrote 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/muvon/octoweb/agents-md)<a href="https://agentmods.dev/instructions/muvon/octoweb/agents-md"><img src="https://agentmods.dev/badge/instructions/muvon/octoweb/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.
<a href="https://agentmods.dev/instructions/muvon/octoweb/agents-md"><img src="https://agentmods.dev/badge/instructions/muvon/octoweb/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.04239 | $0.04239 |
| Opus 5 | $0.02119 | $0.02119 |
| Sonnet 5 | $0.00848 | $0.00848 |
| Haiku 4.5 | $0.00424 | $0.00424 |
Grade A, and why
octoweb 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 2d 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 — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Octoweb Developer Guide
Lightweight macOS browser built on wry/tao. Performance-first, minimal footprint. AI assistant via ACP (Agent Client Protocol). MCP server for external AI tool control.
Architecture
main.rs ← App entry, event loop, WebView pool, keyboard (CGEventTap)
│
├── browser.rs ← TabManager (tabs, history, active state, visit counts)
├── config.rs ← Config, session persistence, favicon cache, prompt history
├── acp.rs ← ACP integration (sidebar AI + background learning agent)
├── mcp.rs ← MCP server — 31 browser control tools over HTTP JSON-RPC
│
├── url.rs ← URL resolution (user input → navigable URL)
├── webview_utils.rs ← Injected JS scripts, favicon cache lookup, overlay data
├── macos.rs ← macOS-specific: dock icon, Edit menu, MRU list, external URLs
├── nav_error_patch.rs ← WKWebView navigation error callbacks (ObjC runtime patch)
├── content_rules.rs ← WKContentRuleList (ad/tracker blocking)
├── crash_report.rs ← WebContent process termination tracking
├── cold_open.rs ← First-run setup, URL scheme handler (kAEGetURL)
├── hibernation.rs ← Session save/restore (tabs, URLs)
├── tab_stats.rs ← Per-tab CPU/RSS stats from WebContent XPC process
├── quickslots.rs ← Fast-access slot logic (⌘⇧1–0 save, ⌘1–0 open)
├── prompt_history_js.rs ← Shared JS module: prompt history nav, Ctrl+R search, ghost text
│
├── page_index.rs ← Full-text index of visited page text (palette `/query`, MCP search tool)
├── later.rs ← Save-for-later queue (⌘⇧L) — decays after later_days, per workspace
├── markdown_js.rs ← Page → markdown walker for ⌥⌘C
├── overlay_html.rs ← Command palette (⌘⇧P) — fuzzy search tabs/history, `/` searches page text
├── sidebar_html.rs ← AI assistant sidebar (⌘⇧A) — chat UI
├── address_bar_html.rs ← Address bar with URL display + AI button
├── inline_edit_html.rs ← Inline AI edit modal (⌘⇧E) — text transformation
├── settings_html.rs ← Settings modal (⌘,)
├── shortcuts_html.rs ← Keyboard shortcuts overlay (⌘/)
├── newtab_html.rs ← New tab page (quick slots, search)
├── find_bar_html.rs ← Find-in-page bar (⌘F)
├── quickslots_html.rs ← Quick slots footer bar UI
├── notification_html.rs ← Toast notification UI
├── error_page_html.rs ← Custom error page for load failures
└── progress_bar_html.rs ← Top-of-screen page load progress bar
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.
- 2d ago First seen · 295 lines · 4,239 tokens per session scan A 436b43ba811b
octoweb AGENTS.md is an instructions file published in the GitHub repository Muvon/octoweb (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 4,239 tokens to every session, about $0.0212 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 2026-09-09.
Other instructions, from other repositories
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.
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 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.
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).
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.