What is agentoscope AGENTS.md?

Repository instructions for Agentoscope, a command-line tool that scans a code repository for AI-agent instruction files and displays them in a browser dashboard. It also checks for issues such as stale file patterns, oversized instructions, and configuration drift.

Use them when adding support for another agent-tool convention, changing repository scanning or glob matching, updating dashboard reports, or running the instruction-file checks.

They explain how instruction files are discovered, classified, connected to repository contexts, and checked. This makes it easier to extend the scanner without breaking its shared analysis logic.

How rafaelcg/agentoscope configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to rafaelcg/agentoscope. 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/rafaelcg/agentoscope/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/rafaelcg/agentoscope

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/rafaelcg/agentoscope/agents-md/github.svg)](https://agentmods.dev/instructions/rafaelcg/agentoscope/agents-md)

Your own site

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

Per session 664 This file is loaded in full into every session.

When invoked 664 The same file — it is already loaded in full.

Security scan A 0 findings. 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	$0.00664	$0.00664
Opus 5.5	$0.00266	$0.00266
Sonnet 5.5	$0.00133	$0.00133
Haiku 4.5	$0.00066	$0.00066

Measured 2mo ago against content hash 3bf9948d0e24, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentoscope 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 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.

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.

AGENTS.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agentoscope — agent instructions

What this is

A zero-runtime-dependency CLI (npx agentoscope) that scans a repo for AI-agent instruction files (AGENTS.md, CLAUDE.md, .cursor/rules, copilot-instructions, …) and renders a self-contained visual dashboard in the browser.

Layout

src/providers.ts — registry of provider conventions. Adding support for a new tool is a single entry in PROVIDERS. Pattern syntax: * one segment, ** any depth, deep: true matches the basename at any depth.
src/scan-core.ts — pure scanning (frontmatter parsing, classification, symlink/duplicate detection). No Node APIs — shared with the CF worker.
src/scanner.ts — filesystem walk on top of scan-core (symlink resolution).
src/glob.ts — dependency-free glob matcher (*, **, ?, {a,b}).
src/report.ts — serializable report model + attach rules (always / subtree / globs / manual) powering --for and the viewer's context view.
src/check.ts — rules linter (stale globs, oversized files, drift, mdc config).
src/inject.ts — embeds the report JSON into the viewer HTML (XSS-safe).
src/cli.ts — arg parsing, check subcommand, local server, browser open.
src/worker.ts — Cloudflare Worker: serves site/, scans public GitHub repos at /r/:owner/:repo (GitHub API + raw fetches, edge-cached 30 min).
src/viewer/ — browser app (app.ts, styles.css, shell.html), bundled into dist/viewer.html with the report embedded as JSON.
build.mjs — esbuild bundles CLI (dist/cli.js), viewer HTML, and the worker (site/_worker.js + site/_viewer.html template, both gitignored).
site/ — landing page (static, deployed to Cloudflare Workers Static Assets via cd site && wrangler deploy; demo.html is a generated sample report).
test/ — vitest; viewer.test.ts runs under jsdom.

Commands

Build: npm run build
Test: npm test
Typecheck: npm run typecheck
All three must pass before publishing (prepublishOnly enforces it).

Read the full file on GitHub · 48 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 · 48 lines · 664 tokens per session scan A 3bf9948d0e24

Subscribe to this mod's changes

agentoscope AGENTS.md is an instructions file published in the GitHub repository rafaelcg/agentoscope (2 stars, last pushed 3mo ago), licensed MIT. It adds 664 tokens to every session, about $0.0027 per session on Opus 5.5. 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.

Building agents

agentoscope AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agentoscope AGENTS.mdrafaelcg/agentoscope	Instructions file	2	3mo ago	MIT	A	664	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	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	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

agentoscope: Instructions file for Codex