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/copilot-instructionsgit 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/copilot-instructions)<a href="https://agentmods.dev/instructions/steffen025/pag-extract/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/steffen025/pag-extract/copilot-instructions.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 | $0.00298 | $0.00298 |
| Opus 5 | $0.00149 | $0.00149 |
| Sonnet 5 | $0.00060 | $0.00060 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade A, and why
pag-extract copilot-instructions.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 4d 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.
What it actually says
GitHub Copilot — instructions for this repository
@AGENTS.md
The line above pulls in this repository's full agent instructions. If your Copilot
surface does not resolve @-includes, open AGENTS.md directly — it is
the single source of truth and this file deliberately holds no copy of it.
Copilot-specific notes
The skill is already wired. .claude/skills/pag-extract/SKILL.md is picked up
without any setup: .claude/skills is one of the skill-discovery paths for both
Copilot CLI and Copilot in VS Code, alongside .github/skills and .agents/skills.
Do not create a .github/skills/pag-extract/ copy — two skills sharing the name
pag-extract is a conflict, not a fallback.
Terminal access is required. The tool is a CLI. Copilot needs permission to run
node (or bun). In Copilot CLI approve the command when prompted, or start the
session in autopilot mode if you want it to run unattended.
Typical one-liner the user will ask for:
node pag-extract.mjs <pag-url-or-INSTANCE/SHORTNAME> --talks --out programme.md
Everything else — options, failure modes, hard rules — is in AGENTS.md.
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.
- 4d ago First seen · 28 lines · 298 tokens per session scan A 6f4e428ddace
pag-extract copilot-instructions.md is an instructions file published in the GitHub repository Steffen025/pag-extract (5 stars, last pushed 1mo ago), licensed MIT. It adds 298 tokens to every session, about $0.0015 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.
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 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.
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.