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 instructions/avdlee/core-data-agent-skill/copilot-instructionsgit clone --depth 1 https://github.com/AvdLee/Core-Data-Agent-SkillWhat 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 | $0.01115 | $0.01115 |
| Opus 5 | $0.00558 | $0.00558 |
| Sonnet 5 | $0.00223 | $0.00223 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
Core-Data-Agent-Skill 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 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.
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.
This is a copy
86% identical to Swift-Concurrency-Agent-Skill copilot-instructions.md — 20 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Instructions: Agent Skills Expert
Review code changes as an Agent Skills expert, focusing on the Agent Skills open format specification and best practices.
Core Agent Skills Principles
Format Compliance
- SKILL.md structure: Every skill must have a
SKILL.mdfile with YAML frontmatter containingnameanddescriptionfields - YAML frontmatter requirements:
name: Maximum 64 characters, lowercase letters/numbers/hyphens only, no XML tags, cannot contain "anthropic" or "claude"description: Non-empty, maximum 1024 characters, no XML tags, must describe both what the skill does AND when to use it
- Progressive disclosure: Skills should be organized in levels (metadata → instructions → resources) to minimize context window usage
- Filesystem-based architecture: Skills exist as directories; files are loaded on-demand via bash commands, not all at once
Skill Content Organization
Level 1: Metadata (always loaded)
- YAML frontmatter in SKILL.md provides discovery information
- Should be concise and trigger-relevant
Level 2: Instructions (loaded when triggered)
- Main SKILL.md body contains procedural knowledge, workflows, best practices
- Should be under ~5k tokens
- Include decision trees, quick reference guides, and clear examples
Level 3: Resources (loaded as needed)
- Additional markdown files for specialized guidance
- Executable scripts for deterministic operations
- Reference materials (schemas, templates, examples)
- Only accessed when referenced, not loaded into context upfront
Review Focus Areas
-
Description Quality
- Does the description clearly state what the skill does?
- Does it specify when an agent should use this skill (trigger conditions)?
- Is it specific enough for accurate skill selection?
-
Instruction Clarity
- Are instructions actionable and step-by-step?
- Do they include decision trees or quick reference guides?
- Are code examples clear and correct?
- Is there a clear "how to use" section?
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 · 100 lines · 1,115 tokens per session scan A 9b6b9abcb75c
Core-Data-Agent-Skill copilot-instructions.md is an instructions file published in the GitHub repository AvdLee/Core-Data-Agent-Skill (302 stars, last pushed 26d ago), licensed MIT. It adds 1,115 tokens to every session, about $0.0056 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to Swift-Concurrency-Agent-Skill copilot-instructions.md, differing in 20 lines, and is treated as a copy.
Other instructions, from other repositories
webmcp-kit AGENTS.md
Instructions for nekuda-ai/webmcp-kit, covering webmcp kit — for agents reading this repo, install, what it does and facts worth carrying.
rig AGENTS.md
Instructions for githubnext/rig, covering agents.md, project overview, architecture, commands and code style.
multica-ops GEMINI.md
Instructions for jamillazarev/multica-ops: This workspace has the multica-ops extension installed. Before acting as Mops — or on any request about building or running a company of AI agents on Multica, a project, features, roles or budgets — read skills/mops/SKILL.md and follow it. The hard gates that must survive…
agent-powerups GEMINI.md
Instructions for yeaight7/agent-powerups, covering project overview, main technologies, architecture/structure, building and running and development conventions.
agentscout AGENTS.md
AGENTS.md instructions for agentx402-ai/agentscout, covering agents.md — agent/contributor guide for this repo, what this repo is, commands, conventions and money-safety invariants (do not weaken).
akidevrule CLAUDE.md
Instructions for lacvietanh/akidevrule, covering akidevrule, project role, source of truth, file naming conventions and rule authoring principles.