Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/ikcode-dev/copilot-kit/kit-copilot-create-core-instructionnpx skills add ikcode-dev/copilot-kit --skill kit-copilot-create-core-instructiongit clone --depth 1 https://github.com/ikcode-dev/copilot-kitWhat 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 | $0.00064 | $0.02031 |
| Opus 5 | $0.00032 | $0.01015 |
| Sonnet 5 | $0.00013 | $0.00406 |
| Haiku 4.5 | $0.00006 | $0.00203 |
Grade B, and why
kit-copilot-create-core-instruction scanned grade B 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 2d 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
- **Always create the file** — Write to `.github/copilot-instructions.md` directly. Never output instructions inline in chat as the final deliverable. How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Core Copilot Instruction
What This Skill Does
Creates a production-ready .github/copilot-instructions.md file — the foundational layer of GitHub Copilot's custom instructions system. This file is attached to every Copilot conversation, providing universal project context that shapes all AI interactions.
Key Concepts: The Layered Instruction Architecture
GitHub Copilot supports a layered approach to custom instructions:
| Layer | File | Scope | Purpose |
|---|---|---|---|
| Core | .github/copilot-instructions.md |
Every conversation | Universal project context |
| Granular | .github/instructions/*.instructions.md |
Matching files only (via applyTo glob) |
File-type-specific or folder-specific conventions |
This skill creates the core layer. The core file must contain only what Copilot needs to know universally — regardless of which file or feature is being worked on. File-type-specific or folder-specific conventions belong in granular instruction files.
The Golden Rule
The core file is attached to every single Copilot conversation. Every line must earn its place.
Content Boundaries
Knowing what belongs in the core file — and what doesn't — is critical for quality.
| Include in Core File | Exclude (Delegate or Omit) |
|---|---|
| Project type and domain context | File-type-specific conventions (→ granular .instructions.md files) |
| Tech stack with versions (brief) | Standard language/framework behaviors |
| Universal naming conventions | Verbose API references |
| Architectural philosophy | Folder-specific patterns (→ granular .instructions.md files) |
| Cross-cutting patterns (errors, logging) | Library documentation |
| Common pitfalls/anti-patterns | Detailed configuration examples |
| Key workflow commands (essential only) | Exhaustive command lists |
| Testing philosophy (not test file specifics) | Test file structure details (→ granular files) |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 172 lines · 64 tokens per session scan B af6bbbd71c69
kit-copilot-create-core-instruction is a skill published in the GitHub repository ikcode-dev/copilot-kit (29 stars, last pushed 5mo ago), licensed MIT. It adds 64 tokens to every session and 2,031 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…