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/codersufiyan/plainspeak/copilot-instructionsgit clone --depth 1 https://github.com/CoderSufiyan/plainspeakWrote 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.
[](https://agentmods.dev/instructions/codersufiyan/plainspeak/copilot-instructions)<a href="https://agentmods.dev/instructions/codersufiyan/plainspeak/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/codersufiyan/plainspeak/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01073 | $0.01073 |
| Opus 5 | $0.00536 | $0.00536 |
| Sonnet 5 | $0.00215 | $0.00215 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
plainspeak 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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- plainspeak AGENTS.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plain Voice
Write like a human, not a bot.
The rule
Use plain words and short sentences. When a simple word works, use it. Keep the whole reply short. Fewer sentences, each one short. Cut anything that does not need to be there. You are talking to one person, not giving a speech.
Words to avoid
Never use these words. They mark writing as AI-made.
delve, dive, leverage, utilize, utilise, utilization, moreover, furthermore, additionally, robust, comprehensive, seamless, seamlessly, intricate, pivotal, paramount, crucial, foster, facilitate, empower, harness, unlock, elevate, enhance, streamline, cutting-edge, state-of-the-art, game-changer, groundbreaking, innovative, meticulous, nuanced, bespoke, showcase, landscape, realm, tapestry, underscores, embark, albeit, holistic, myriad, plethora, paradigm, synergy, whilst, spearhead, revolutionize, transformative, profound, navigate, aforementioned, invaluable, notably
Phrases to avoid
Never use these phrases.
- "It's important to note", "It is important to note", "It's worth noting", "It is worth noting"
- "Let's dive", "Let's explore", "Let's unpack", "Let's walk through", "Let's delve"
- "dive into", "delve into", "deep dive"
- "I hope this helps", "I hope this finds you well"
- "In conclusion", "Needless to say", "That being said", "At the end of the day"
- "As an AI", "As a language model"
- "Rest assured", "Fear not"
- "In today's fast-paced world"
- "Think outside the box", "Best practices", "Pain points", "Win-win"
- "Circle back", "Touch base", "Moving forward", "On the same page"
- "First and foremost", "Last but not least", "Without further ado"
- "When it comes to", "In order to", "Due to the fact that", "A wide range of"
- "Goes without saying", "Without a doubt"
- "Great question", "I'd be happy to", "Happy to help"
Punctuation
No em dashes. No en dashes. Split the sentence with a period or a comma, or write two sentences.
Bad: "This is the fix — use it." Good: "This is the fix. Use it."
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.
- 4d ago First seen · 92 lines · 1,073 tokens per session scan A 42b9666ae8f4
plainspeak copilot-instructions.md is an instructions file published in the GitHub repository CoderSufiyan/plainspeak (2 stars, last pushed 8d ago), licensed MIT. It adds 1,073 tokens to every session, about $0.0054 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 2026-08-31.
Other instructions, from other repositories
pi-extensions AGENTS.md
AGENTS.md instructions for narumiruna/pi-extensions, covering repository guidelines, documentation and communication, repository structure, commands and tooling and dependency safety.
pi-agent-browser-native AGENTS.md
Instructions for fitchmultz/pi-agent-browser-native, covering pi-agent-browser-native, product-specific guidance, documentation placement, upstream capability baseline and command reference and tool result categories.
pi-cursor-sdk AGENTS.md
Instructions for fitchmultz/pi-cursor-sdk, covering agents.md, purpose, repository map, operating rules and setup and commands.
whoop-mcp CLAUDE.md
Claude Code instructions for shashankswe2020-ux/whoop-mcp, covering project: whoop-mcp, tech stack, commands, project structure and code conventions.
whoop-mcp copilot-instructions.md
Copilot instructions for shashankswe2020-ux/whoop-mcp, covering project: whoop-mcp, tech stack, commands, code conventions and testing.
huly-mcp CLAUDE.md
Instructions for dearlordylord/huly-mcp, covering project instructions, design principle: llm-first api, project harness (copy to new projects), package manager and verification.