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/steffen025/pag-extract/agents-mdgit clone --depth 1 https://github.com/Steffen025/pag-extractWrote 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/steffen025/pag-extract/agents-md)<a href="https://agentmods.dev/instructions/steffen025/pag-extract/agents-md"><img src="https://agentmods.dev/badge/instructions/steffen025/pag-extract/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 | $0.01410 | $0.01410 |
| Opus 5 | $0.00705 | $0.00705 |
| Sonnet 5 | $0.00282 | $0.00282 |
| Haiku 4.5 | $0.00141 | $0.00141 |
Grade A, and why
pag-extract 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.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions for AI agents
This file tells coding agents (GitHub Copilot, Claude Code, ChatGPT Codex, Cursor, Windsurf, Aider, Gemini CLI, …) how to use this repository. Read it before doing anything else.
Where your instructions live
Nothing here needs to be copied or configured. This repository ships its instructions in the files each tool already reads:
| File | Read by |
|---|---|
AGENTS.md (this file) |
GitHub Copilot (CLI + coding agent), Codex, Cursor, Claude Code, Gemini CLI, Aider |
.github/copilot-instructions.md |
GitHub Copilot (CLI, VS Code, cloud agent) — a pointer that @-includes this file, never a copy of it |
CLAUDE.md |
Claude Code, GitHub Copilot CLI |
.claude/skills/pag-extract/SKILL.md |
Claude Code and GitHub Copilot (CLI + VS Code) — .claude/skills is a skill-discovery path for all of them, alongside .github/skills and .agents/skills |
This file is the single source of truth. The Copilot and Claude entry points are
pointers into it. Do not create a .github/skills/pag-extract/ copy of the skill: every
listed tool already scans .claude/skills, and two skills sharing the name
pag-extract is a conflict rather than a fallback.
What this repository is
A single-file CLI that reads the public programme of a congress running on the m-anage / VMX platform and writes it out as Markdown, CSV or JSON.
- Entry point:
pag-extract.mjs— plain ESM JavaScript, zero dependencies, no build step - Runtime: Node >= 18 or Bun >= 1.0
- Interface reference:
docs/API.md
The task users will ask you for
Almost always one of these:
"Read the programme at
<URL>and save it as<file>." "Which talks at<congress>are about<topic>?" "Give me a schedule for<day>."
How to do it
Run the tool. Do not write new fetching code, and do not scrape the HTML page.
# whole programme incl. individual talks, as Markdown
node pag-extract.mjs <pag-url-or-INSTANCE/SHORTNAME> --talks --out programme.md
# one day only
node pag-extract.mjs MCON/kkj2026 --day 2026-11-19 --out day.md
# tabular, for spreadsheets
node pag-extract.mjs MCON/kkj2026 --talks --format csv --out programme.csv
# structured, for your own filtering
node pag-extract.mjs MCON/kkj2026 --talks --format json --out programme.json
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 · 116 lines · 1,410 tokens per session scan A 72ad868e8172
pag-extract AGENTS.md is an instructions file published in the GitHub repository Steffen025/pag-extract (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,410 tokens to every session, about $0.0070 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
bun AGENTS.md
AGENTS.md instructions for oven-sh/bun, a project described as: Incredibly fast JavaScript runtime, bundler, test runner, and package manager – all in one.
webjs AGENTS.md
AGENTS.md instructions for webjsdev/webjs, covering agents.md for webjs, ai-driven development: guardrails for all agents, before starting any work: verify and sync the branch, one task per git worktree, always and skills are routed deterministically, never skipped.
bun CLAUDE.md
Claude Code instructions for oven-sh/bun, covering building and running bun, build commands, changes that don't require a build, testing and running tests.
webjs copilot-instructions.md
Copilot instructions for webjsdev/webjs, covering github copilot instructions: webjs app, persistence + scaffold rules (non-negotiable), before starting any work, autonomous mode (sandbox / no-prompt) and mandatory workflow (never skip).
morph AGENTS.md
Instructions for vseplet/morph, covering morph — documentation for ai agents, project setup, file structure (minimal), file structure (recommended) and dependencies.
mbun CLAUDE.md
Claude Code instructions for Sunrisepeak/mbun: This project uses the hagent AI Agent open-source collaboration spec.