mnemonic plugin-files.instructions.md

A set of writing rules for Claude Code plugin files, including commands, skills, and agents. It defines the required file layout, metadata, and content sections.

In plain words
What is it for?
Use it when creating or reviewing plugin commands, skills, or agents, including their instructions, examples, error handling, workflows, and related references.
Why use it?
It gives contributors a consistent way to structure plugin files, so tools and instructions are easier to understand and maintain.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/modeled-information-format/mnemonic/plugin-files
Clone the repo
git clone --depth 1 https://github.com/modeled-information-format/mnemonic

Made for: GitHub Copilot.

Per session 222 This file is loaded in full into every session.
When invoked 222 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00222 $0.00222
Opus 5 $0.00111 $0.00111
Sonnet 5 $0.00044 $0.00044
Haiku 4.5 $0.00022 $0.00022

Measured 2d ago against content hash f34e192989cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mnemonic plugin-files.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.

.github/instructions/plugin-files.instructions.md · 60 lines

What it actually says

Claude Code Plugin File Guidelines

Commands (commands/*.md)

Required frontmatter:

---
name: command-name
description: Brief description of what the command does
---

Content structure:

  • Clear usage instructions
  • Examples with expected behavior
  • Error handling guidance

Skills (skills/*/SKILL.md)

Required frontmatter:

---
name: skill-name
description: What this skill provides
---

Content structure:

  • Domain knowledge and context
  • Step-by-step procedures
  • Decision criteria
  • Examples and templates

Agents (agents/*.md)

Required frontmatter:

---
name: agent-name
description: Agent's purpose and capabilities
---

Content structure:

  • Agent role and responsibilities
  • Available tools and actions
  • Workflow patterns
  • Integration points

General Guidelines

  • Use clear, imperative language
  • Include practical examples
  • Reference related commands/skills
  • Keep frontmatter minimal but complete
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. 2d ago First seen · 60 lines · 222 tokens per session scan A f34e192989cd

Subscribe to this mod's changes

mnemonic plugin-files.instructions.md is an instructions file published in the GitHub repository modeled-information-format/mnemonic (22 stars, last pushed 1mo ago), licensed MIT. It adds 222 tokens to every session, about $0.0011 per session on Opus 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.

Related

Other instructions, from other repositories