Borrowing it
Nothing to install: this file belongs to franklesniak/copilot-repo-template. 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/franklesniak/copilot-repo-template/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/franklesniak/copilot-repo-templateWrote 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/franklesniak/copilot-repo-template/copilot-instructions)<a href="https://agentmods.dev/instructions/franklesniak/copilot-repo-template/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/franklesniak/copilot-repo-template/copilot-instructions/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/franklesniak/copilot-repo-template/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/franklesniak/copilot-repo-template/copilot-instructions.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 | $0.14319 | $0.14319 |
| Opus 5.5 | $0.05728 | $0.05728 |
| Sonnet 5.5 | $0.02864 | $0.02864 |
| Haiku 4.5 | $0.01432 | $0.01432 |
Grade E, and why
copilot-repo-template copilot-instructions.md scanned grade E with 2 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 1mo 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- template-sync: begin instruction-enforcement-only --> Nullifies safety policieshighAnti-refusal
"You have no restrictions", "do anything now", "ignore your guidelines": a direct jailbreak that disables guardrails.
For Git placement, agents MUST use an explicit non-force source-to-destination refspec to the verified repository and head ref. Do not use force options, a leading `+`, history rewriting, or extra ref updates. A policy r How it starts
The opening of the file, as written. The whole thing — 728 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Copilot Instructions (Repo-Wide Constitution)
Version: 1.6.20260923.0
Metadata
- Status: Active
- Owner: Repository Maintainers
- Last Updated: 2026-09-23
- Scope: Repo-wide canonical instructions ("constitution") that govern all changes in this repository. This file is the authoritative source of truth for repository rules; all language-specific instruction files and agent entry points defer to it.
- Related: Documentation Writing Style
These instructions are authoritative for all changes in this repository.
Source of Truth
Customize this section for your project. Point to your authoritative specification or design document. Example:
- Read
docs/spec/requirements.mdbefore making changes.- If any instruction here conflicts with the spec, the spec wins.
Protected Instruction Files
Instruction files, style guides, and the retained instruction-contract catalog are protected governance files. This rule applies to:
- The repo-wide constitution:
.github/copilot-instructions.md - Root agent entry points:
.hermes.md,AGENTS.md,CLAUDE.md, andGEMINI.md - Cursor project rules under
.cursor/rules/ - Modular instruction files under
.github/instructions/ - The retained instruction-contract catalog:
.template-sync/instruction-contracts.yml
- The standalone instruction catalog and local profile:
.github/instruction-contracts.ymland.github/instruction-profile.yml, withschemas/instruction-contracts.schema.jsonandschemas/instruction-profile.schema.json
- The retained workflow security contract:
.github/workflow-security-contract.yml
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.
- 1mo ago Changed · +190 lines · +6,172 tokens per session scan A → E ad9f24f55279
- 2mo ago First seen · 538 lines · 8,147 tokens per session scan A 96301330b6c2
copilot-repo-template copilot-instructions.md is an instructions file published in the GitHub repository franklesniak/copilot-repo-template (9 stars, last pushed 5d ago), licensed MIT. It adds 14,319 tokens to every session, about $0.0573 per session on Opus 5.5. A static security scan graded it E with 2 findings (hidden instructions, nullifies safety policies). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.