agentmods.dev

knocoph: Instructions file for GitHub Copilot

.github/copilot-instructions.md

knocoph copilot-instructions.md is an instructions file for GitHub Copilot from jagonzalr/knocoph. It costs 842 tokens per session, scanned A, original, MIT.

Instructions for using Knocoph, a persistent knowledge graph of a codebase. A knowledge graph maps code symbols and their relationships so an agent can inspect structure before opening files.

In plain words
What is it for?
Use it to explore a repository, find symbols, inspect callers and dependencies, understand architecture, and refresh the graph after code changes.
Why use it?
It helps the agent locate relevant code, understand dependencies, and estimate the impact of changes before editing source files.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

This is jagonzalr/knocoph's own configuration. It tells GitHub Copilot how to work on knocoph 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 knocoph configures →

not rated 0repo 3mo ago A scan 842 tokens original MIT
View source ↗ jagonzalr/knocoph npmjs.com
Reuse

Borrowing it

Nothing to install: this file belongs to jagonzalr/knocoph. 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/jagonzalr/knocoph/main/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/jagonzalr/knocoph

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 knocoph copilot-instructions.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jagonzalr/knocoph/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/jagonzalr/knocoph/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 842 This file is loaded in full into every session.
When invoked 842 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 $0.00842 $0.00842
Opus 5.5 $0.00337 $0.00337
Sonnet 5.5 $0.00168 $0.00168
Haiku 4.5 $0.00084 $0.00084

Measured 2mo ago against content hash fdb0f8035443, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

knocoph 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.github/copilot-instructions.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using Knocoph (Code Knowledge Graph)

This project is indexed with Knocoph. A persistent code knowledge graph is available via MCP tools. Use graph tools first — before reading files. This gives faster, more accurate structural answers and uses far fewer context tokens.

Rule: graph before files

  1. Call find_symbol to locate any symbol by name. Use include_snippet: true to get the source code in the same call.
  2. Call get_neighbors with a symbol name or node_id to explore what it calls and what calls it, before reading the file it lives in.
  3. Call explain_impact with a symbol name or node_id before modifying any symbol to understand blast radius and dependency paths.
  4. Call codebase_overview at the start of any analysis to understand the project's structure, file count, symbol distribution, and top-level architecture.
  5. Call query_architecture to understand what symbols a file defines and what it imports/exports before reading the file.
  6. Call get_snippet to read specific lines from a file when you have file_path and line numbers from a previous tool result.
  7. Call index_project if the graph appears stale after code changes. tsconfig.json is auto-detected at the project root for path alias resolution — pass tsconfig_path explicitly if it lives elsewhere.

Tool selection guide

Question Tool
Overview of symbols and relationships? codebase_overview { }
Where is UserService defined? find_symbol { name: "UserService" }
Show me the body of create find_symbol { name: "create", include_snippet: true }
What does UserService call? get_neighbors { name: "UserService", direction: "outgoing" }
What calls UserService? get_neighbors { name: "UserService", direction: "incoming" }
What breaks if I change createUser? explain_impact { name: "createUser" }
Why does createUser exist? explain_impact { name: "createUser" }
What does this file export and import? query_architecture { file_path }
Read lines 50-80 of a file get_snippet { file_path, start_line: 50, end_line: 80 }
Graph returns empty results index_project { root_dir: "." }
Non-root or monorepo tsconfig index_project { root_dir: ".", tsconfig_path: "./packages/app/tsconfig.json" }

Read the full file on GitHub · 48 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. 2mo ago First seen · 48 lines · 842 tokens per session scan A fdb0f8035443

Subscribe to this mod's changes

knocoph copilot-instructions.md is an instructions file published in the GitHub repository jagonzalr/knocoph (0 stars, last pushed 3mo ago), licensed MIT. It adds 842 tokens to every session, about $0.0034 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 2026-08-31.

Memory and contextcode-analysisjavascriptknowledge-graphmcp
Related

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

knocoph copilot-instructions.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
knocoph copilot-instructions.mdjagonzalr/knocophInstructions file03mo agoMITA842GitHub 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