agentmods.dev

Ctxo: Instructions file for GitHub Copilot

.github/copilot-instructions.md

Ctxo copilot-instructions.md is an instructions file for GitHub Copilot from alperhankendi/Ctxo. It costs 408 tokens per session, scanned A, original, MIT.

A set of project instructions for using the Ctxo MCP tools before exploring code, changing it, or reviewing changes. MCP tools are connected tools that provide information about a codebase and its dependencies.

In plain words
What is it for?
Use it in the Ctxo project when fixing bugs, adding features, refactoring, understanding code, searching for symbols, or reviewing a pull request or code diff.
Why use it?
It makes the agent check related code, past changes, and likely effects before editing. This helps avoid changes that break dependent parts of the project.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

This is alperhankendi/Ctxo's own configuration. It tells GitHub Copilot how to work on Ctxo itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Ctxo configures →

not rated 74repo 5d ago A scan 408 tokens original MIT
View source ↗ alperhankendi/Ctxo alperhankendi.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to alperhankendi/Ctxo. 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/alperhankendi/Ctxo/master/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/alperhankendi/Ctxo

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 Ctxo copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/alperhankendi/ctxo/copilot-instructions/github.svg)](https://agentmods.dev/instructions/alperhankendi/ctxo/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/alperhankendi/ctxo/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/alperhankendi/ctxo/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.

agentmods 80×15 button for Ctxo copilot-instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/alperhankendi/ctxo/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/alperhankendi/ctxo/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 408 This file is loaded in full into every session.
When invoked 408 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00408 $0.00408
Opus 5.5 $0.00163 $0.00163
Sonnet 5.5 $0.00082 $0.00082
Haiku 4.5 $0.00041 $0.00041

Measured 2mo ago against content hash bd16e8ceabe6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Ctxo 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 2mo 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 · 34 lines

What it actually says

ctxo MCP Tool Usage (MANDATORY)

ALWAYS use ctxo MCP tools before reading source files or making code changes. The ctxo index contains dependency graphs, git intent, anti-patterns, and change health that cannot be derived from reading files alone. Skipping these tools leads to blind edits and broken dependencies.

Before ANY Code Modification

  1. Call get_blast_radius for the symbol you are about to change — understand what breaks
  2. Call get_why_context for the same symbol — check for revert history or anti-patterns
  3. Only then read and edit source files

Before Starting a Task

Task Type REQUIRED First Call
Fixing a bug get_context_for_task(taskType: "fix")
Adding/extending a feature get_context_for_task(taskType: "extend")
Refactoring get_context_for_task(taskType: "refactor")
Understanding code get_context_for_task(taskType: "understand")

Before Reviewing a PR or Diff

  • Call get_pr_impact — single call gives full risk assessment with co-change analysis

When Exploring or Searching Code

  • Use search_symbols for name/regex lookup — DO NOT grep source files for symbol discovery
  • Use get_ranked_context for natural language queries — DO NOT manually browse directories

Orientation in Unfamiliar Areas

  • Call get_architectural_overlay to understand layer boundaries
  • Call get_symbol_importance to identify critical symbols

NEVER Do These

  • NEVER edit a function without first calling get_blast_radius on it
  • NEVER skip get_why_context — reverted code and anti-patterns are invisible without it
  • NEVER grep source files to find symbols when search_symbols exists
  • NEVER manually trace imports when find_importers gives the full reverse dependency graph
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. 2mo ago First seen · 34 lines · 408 tokens per session scan A bd16e8ceabe6

Subscribe to this mod's changes

Ctxo copilot-instructions.md is an instructions file published in the GitHub repository alperhankendi/Ctxo (74 stars, last pushed 5d ago), licensed MIT. It adds 408 tokens to every session, about $0.0016 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.

ai-codingclaudecode-intelligencecodebase-contextcopilotcursor
Related

Ctxo copilot-instructions.md compared with instructions from other repositories

Ctxo copilot-instructions.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Ctxo copilot-instructions.mdalperhankendi/CtxoInstructions file745d agoMITA408GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode