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/hiroki-org/jules-extension/copilot-instructionsgit clone --depth 1 https://github.com/Hiroki-org/jules-extensionWrote 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/hiroki-org/jules-extension/copilot-instructions)<a href="https://agentmods.dev/instructions/hiroki-org/jules-extension/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/hiroki-org/jules-extension/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 | $0.03176 | $0.03176 |
| Opus 5 | $0.01588 | $0.01588 |
| Sonnet 5 | $0.00635 | $0.00635 |
| Haiku 4.5 | $0.00318 | $0.00318 |
Grade A, and why
jules-extension 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 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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jules Extension - Copilot Instructions
Jules Extension is a TypeScript-based VS Code extension for creating, monitoring, and reviewing Google Jules coding sessions directly inside VS Code. It also handles GitHub authentication, PR status checks, diff viewing, and branch operations. This repository is a single-package extension project. Source code lives in src/, production output lives in dist/, and compiled test output lives in out/.
In this repository, the job is not finished when a PR is opened. A task is only complete after review conversations have replies, conversations are resolved, and CI has been monitored through completion. The gh workflow and the repeated sleep 300 && gh pr checks <PR#> loop are mandatory operating procedures here.
Quick Reference
| Item | Tech / Responsibility | Location |
|---|---|---|
| Extension core | TypeScript, VS Code Extension API | src/extension.ts |
| Jules API integration | Google Jules API client | src/julesApiClient.ts |
| GitHub integration | OAuth, repo URL, PR helpers | src/githubAuth.ts, src/githubUtils.ts |
| UI | Tree View, Chat View, Document Provider | src/chatView.ts, src/planDocumentProvider.ts |
| Session diff support | Diff, changeset, artifacts | src/sessionArtifacts.ts, src/sessionContextMenuArtifacts.ts |
| Security helpers | Log sanitization, URL credential stripping | src/securityUtils.ts |
| Tests | Mocha + vscode-test |
src/test/ |
| Build | esbuild | esbuild.js, dist/ |
| CI | GitHub Actions, pnpm, Node 20/22 | .github/workflows/ |
Project Overview
This project is not a monorepo. The repository contains a single VS Code extension package with its code and configuration at the root.
- The extension manages Jules sessions, activities, chat, plan approval, PR opening, and diff inspection inside VS Code.
- GitHub auth and PR visibility are first-class features. Remote branch state, PR URL resolution, and GitHub sign-in flows are easy to break and must be treated carefully.
- Security-sensitive logging behavior is explicit in this codebase. Sanitization and credential stripping are part of the supported behavior, not optional cleanup.
- Do not hand-edit generated outputs in
dist/orout/. Editsrc/and regenerate through the normal build and test flow.
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 · 325 lines · 3,176 tokens per session scan A 494d1fa655f8
jules-extension copilot-instructions.md is an instructions file published in the GitHub repository Hiroki-org/jules-extension (19 stars, last pushed 2d ago), licensed MIT. It adds 3,176 tokens to every session, about $0.0159 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 2026-08-30.
Other instructions, from other repositories
jules GEMINI.md
Instructions for gemini-cli-extensions/jules, covering jules extension, command: /jules, activation and response, starting a jules task and jules-related queries.
gemini-rules-repo GEMINI.md
Instructions for sanpicule/gemini-rules-repo, covering gemini 開発ルール, 1. コミットメッセージ, 2. セキュリティ, 3. ブランチモデル and ブランチの種類.
render-claude-context CLAUDE.md
Instructions for czottmann/render-claude-context, covering claude.md, project overview, key files, core architecture and file processing system (index.js:7-30).
desmond CLAUDE.md
Claude Code instructions for llegomark/desmond, covering claude.md, project overview, development commands, essential commands and build notes.
awesome-gemini GEMINI.md
Instructions for aaronhuff/awesome-gemini, covering welcome to the gemini documentation, introduction to gemini, getting started, project structure and gems.
deep-research GEMINI.md
Gemini CLI instructions for ssdeanx/deep-research, covering deep research assistant - project context, project overview, core technologies & architecture, primary framework and ai & ml stack.