Copilot-Skills copilot-instructions.md

Copilot-Skills copilot-instructions.md is an instructions file for GitHub Copilot from TheSethRose/Copilot-Skills. It costs 6,199 tokens per session, scanned A, original, MIT.

Repository instructions for using Copilot Skills, including a command-line tool called Kit for finding symbols, searching code, and viewing file context. They also describe how to coordinate work across specialist agents.

In plain words
What is it for?
Use them when searching or editing that repository, tracing symbol usage, gathering code context, reviewing the file tree, or coordinating implementation work.
Why use it?
They help contributors inspect related code before editing and follow the repository's required process for understanding and changing files.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file. Also seen: mentions subagents.

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is uv run --with cased-kit python .github/scripts/kit/bootstrap.py # After major changes.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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.

agentmods badge for Copilot-Skills copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/thesethrose/copilot-skills/copilot-instructions.svg)](https://agentmods.dev/instructions/thesethrose/copilot-skills/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/thesethrose/copilot-skills/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/thesethrose/copilot-skills/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,199 This file is loaded in full into every session.
When invoked 6,199 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.06199 $0.06199
Opus 5 $0.03099 $0.03099
Sonnet 5 $0.01240 $0.01240
Haiku 4.5 $0.00620 $0.00620

Measured 5d ago against content hash 102635472a05, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Copilot-Skills copilot-instructions.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Queue single review: `curl -X POST http://localhost:3010/api/reviews/scan/{businessId}`
.github/copilot-instructions.md · 586 lines

How it starts

The opening of the file, as written. The whole thing — 586 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions

CRITICAL: For ANY file operation (C.R.U.D., search, grep, etc.), ALWAYS use Kit first:

Before reading, searching, or modifying ANY file:

# Find what you're looking for
kit symbols . --format json | jq '.[] | select(.name == "FUNCTION_NAME")'  # Find function
kit grep . "SEARCH_TERM" --directory "src"                                # Search in directory
kit usages . "SYMBOL_NAME"                                               # Find usages

# Get file context before editing
kit context . src/file.ts 42                                             # Get code around line
kit chunk-symbols . src/file.ts                                          # Split file by functions

# Understand related code
kit file-tree . --path src/pages                                         # View structure
cat .kit-analysis/summary.md                                             # See most complex files

Why: Kit is 25-36x faster than grep, excludes node_modules automatically, and gives structured output.

This is MANDATORY for every task. Do not skip Kit.


Orchestration Default

  • Treat every user query as an orchestration task: decide which specialist agents in /.github/agents/ to involve before replying.
  • Prefer breaking work into targeted subagents when tasks can be split; call them via the runSubagent tool and merge their outputs into one concise answer.
  • If no suitable agent exists or delegation adds no value, proceed directly but mention that delegation was considered.
  • Keep added narration minimal and honor all existing workflows (Kit-first, patching rules, testing, quirks).

Project Overview

DiscoverAnnaTX is a production-ready local business directory with AI-powered business review generation. It's a full-stack TypeScript application combining React frontend with Node.js/Express backend, featuring Redis-backed async job processing for website scraping and AI analysis.

Current Phase: AI review system operational with BullMQ job queue, Puppeteer web scraping, OpenRouter Claude/Gemini AI integration, and Stripe monetization (3 revenue streams: Category Sponsorship $299.99/mo, 50 Lead Credits $99.99, 10 Lead Credits $49.99)

Read the full file on GitHub · 586 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.

  1. 5d ago First seen · 586 lines · 6,199 tokens per session scan A 102635472a05

Subscribe to this mod's changes

Copilot-Skills copilot-instructions.md is an instructions file published in the GitHub repository TheSethRose/Copilot-Skills (3 stars, last pushed 9mo ago), licensed MIT. It adds 6,199 tokens to every session, about $0.0310 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories