What is sensei copilot-instructions.md?

A repository guide for Sensei, a coding-agent skill that checks and improves SKILL.md front-matter compliance. SKILL.md is the file containing an agent skill’s runtime instructions.

Use it when authoring or reviewing agent skills. It helps maintain SKILL.md metadata, route users with clear trigger phrases, organize supporting documents, and run the project’s validation tools.

It separates operational instructions from human documentation and sets rules for descriptions, references, examples, and token or scoring checks.

How spboyer/sensei configures GitHub Copilot

Reuse

Borrowing it

Nothing to install: this file belongs to spboyer/sensei. 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/spboyer/sensei/main/.github/copilot-instructions.md

Clone the repo

git clone --depth 1 https://github.com/spboyer/sensei

Made for: GitHub Copilot.

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/spboyer/sensei/copilot-instructions/github.svg)](https://agentmods.dev/instructions/spboyer/sensei/copilot-instructions)

Your own site

<a href="https://agentmods.dev/instructions/spboyer/sensei/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/spboyer/sensei/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/spboyer/sensei/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/spboyer/sensei/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 678 This file is loaded in full into every session.

When invoked 678 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	$0.00678	$0.00678
Opus 5.5	$0.00271	$0.00271
Sonnet 5.5	$0.00136	$0.00136
Haiku 4.5	$0.00068	$0.00068

Measured 7d ago against content hash 6038d79a87cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sensei 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 7d 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.

.github/copilot-instructions.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions

Follow AGENTS.md as the canonical contributor guidance for this repository. This file summarizes the highest-impact rules for GitHub Copilot and Copilot Coding Agent.

Project Context

This repository is Sensei, an Agent Skill that improves SKILL.md frontmatter compliance. The root SKILL.md is the runtime skill; README.md is human-facing documentation; references/ contains progressive-disclosure docs; scripts/ contains the TypeScript token/scoring CLI and optional GEPA evaluator.

Skill Authoring Rules

Keep SKILL.md focused on operational instructions, not README-style documentation.
Put detailed explanations, examples, and templates under references/.

Preserve Agent Skills frontmatter format:

---
name: skill-name
description: "**WORKFLOW SKILL** - What the skill does. WHEN: \"trigger 1\", \"trigger 2\", \"trigger 3\". INVOKES: tools used. FOR SINGLE OPERATIONS: when to bypass."
---

Prefer positive routing with WHEN: / USE FOR: trigger phrases.
Default to concise positive scope; test negative boundaries with near-miss prompts.
Keep description fields under 1024 characters.
Use inline double-quoted descriptions, not folded YAML scalars.
Use skill type prefixes consistently: **WORKFLOW SKILL**, **UTILITY SKILL**, or **ANALYSIS SKILL**.

These routing labels, type prefixes, inline description style, 150-character/60-word targets, and 500-token target are Sensei conventions, not portable-spec requirements. Do not pad useful short descriptions. The standard requires name and description; missing license/version is advisory only. Keep specChecks separate from optional checks, and distinguish static scoring/GEPA keyword fitness from observed host activation. See references/portability.md for host-specific limitations.

Token and Scoring Expectations

Target SKILL.md at about 500 tokens; enforce repository-configured check limits.
Keep references/*.md near 2000 tokens or less.
Target Medium-High or High advisory score:
- Medium-High: trigger phrases with a concise description.
- High: Medium-High plus routing clarity such as INVOKES: and FOR SINGLE OPERATIONS:.

Read the full file on GitHub · 62 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.

7d ago Changed · +7 lines · +96 tokens per session 6038d79a87cb
2mo ago First seen · 55 lines · 582 tokens per session scan A fe9583ed6753

Subscribe to this mod's changes

sensei copilot-instructions.md is an instructions file published in the GitHub repository spboyer/sensei (60 stars, last pushed yesterday), licensed MIT. It adds 678 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 2026-08-30.

Building agents claude copilot gemeni quality skills testing-tools

sensei copilot-instructions.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sensei copilot-instructions.mdspboyer/sensei	Instructions file	60	yesterday	MIT	A	678	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

sensei: Instructions file for GitHub Copilot