agentmods.dev

aipm: Instructions file for GitHub Copilot

.github/copilot-instructions.md

aipm copilot-instructions.md is an instructions file for GitHub Copilot from bluelilyc/aipm. It costs 480 tokens per session, scanned A, original, MIT.

Project-specific instructions for AIPM, a TypeScript command-line tool that installs template packs for GitHub Copilot and Claude. They describe its architecture, file layout, build setup, and installation conventions.

In plain words
What is it for?
Use them when modifying AIPM commands, template discovery or installation, Copilot or Claude output, MCP configuration merging, builds, or tests.
Why use it?
They give coding agents the context needed to change this repository without breaking its command flow or template formats. They also record rules for workspace packages, generated bundles, and copied configuration files.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file. Also seen: mentions .claude-plugin.

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

not rated 1repo 6mo ago A scan 480 tokens original MIT
View source ↗ bluelilyc/aipm
Reuse

Borrowing it

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

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 aipm copilot-instructions.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bluelilyc/aipm/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/bluelilyc/aipm/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 480 This file is loaded in full into every session.
When invoked 480 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 $0.00480 $0.00480
Opus 5.5 $0.00192 $0.00192
Sonnet 5.5 $0.00096 $0.00096
Haiku 4.5 $0.00048 $0.00048

Measured 2mo ago against content hash 00ca8b981a7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aipm 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 · 26 lines

What it actually says

Copilot instructions

Project overview

  • AIPM is a TypeScript ESM CLI that installs template packs for Copilot/Claude. The CLI entry point is src/cli.ts and the library surface is src/index.ts.
  • The build is a Vite library bundle targeting Node 18 with ESM output; entry points are cli and index in vite.config.ts.

Core architecture and flow

  • aipm install (Commander) resolves a templates root, computes a target path, and calls installTemplates from src/installer.ts.
  • installTemplates scans a template pack via findTemplateFiles (agents, prompts, instructions, skills, MCP config) and copies files into the target. Copilot installs go to .github, Claude installs go to .claude/<pack> and also write .claude-plugin/plugin.json.
  • aipm list uses listTemplateManifests and formatTemplateTable in src/listing.ts.

Template and MCP conventions

  • Template packs live under templates/ and typically include agents/, prompts/, instructions/, optional skills/*.skill/, and a template.json manifest (metadata only; not installed).
  • MCP config files are copied as mcp.json for Copilot and .mcp.json for Claude. mergeMcpConfig merges only new server keys and skips invalid configs or duplicates; it never overwrites existing servers.

Developer workflows

  • Build: npm run build (Vite lib build). Watch: npm run dev.
  • Tests: npm test (Vitest; see tests/).
  • Typecheck: npm run typecheck.
  • Format: npm run format.

Project-specific conventions

  • TypeScript uses ESM imports with explicit .js extensions (e.g., ./installer.js) because the output is ESM.
  • Use Node fs/promises and path helpers consistently, as in src/installer.ts.
  • Follow additional instructions under .github/instructions/ for specific file types.
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 · 26 lines · 480 tokens per session scan A 00ca8b981a7d

Subscribe to this mod's changes

aipm copilot-instructions.md is an instructions file published in the GitHub repository bluelilyc/aipm (1 stars, last pushed 6mo ago), licensed MIT. It adds 480 tokens to every session, about $0.0019 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.

Building agents
Related

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

aipm copilot-instructions.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
aipm copilot-instructions.mdbluelilyc/aipmInstructions file16mo agoMITA480GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, 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