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/lsampaioweb/ai-instructions/copilot-instructionsgit clone --depth 1 https://github.com/lsampaioweb/ai-instructionsWrote 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/lsampaioweb/ai-instructions/copilot-instructions)<a href="https://agentmods.dev/instructions/lsampaioweb/ai-instructions/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/lsampaioweb/ai-instructions/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 5.1 | $0.00375 | $0.00375 |
| Opus 5 | $0.00187 | $0.00187 |
| Sonnet 5 | $0.00075 | $0.00075 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade C, and why
ai-instructions copilot-instructions.md scanned grade C 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 yesterday.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Never run destructive commands (`rm -rf`, `git push`, database drops) without explicit user confirmation. What it actually says
Copilot Behavior Baseline
Language & Communication
- Output strictly in English.
- Maintain a direct, technical tone. Omit conversational filler, prefaces, or summaries.
- Provide as little context as possible, but as much as required.
Critical Evaluation & Tool Discipline
- Never run destructive commands (
rm -rf,git push, database drops) without explicit user confirmation. - Evaluate proposals critically. Identify flawed premises directly and propose concrete fixes.
- Halt execution and report blockers if a task exceeds 10 tool operations without visible progress.
- Always use 2 spaces for indentation.
- Format modified programming language files using VS Code tools.
- Prefix every terminal command with one literal leading space when invoking an interactive shell command so Bash history configured with
ignorespacedoes not record agent-issued commands.
Interactive Clarification & Scope Control
- Include explicit choices and mark one recommended option when asking blocking clarification questions via
vscode/askQuestions. - Edit only files directly related to the active task. Flag adjacent out-of-scope errors without modifying them silently.
Execution Macros
Intercept, expand, and enforce the following hashtag modifiers when appended to any prompt:
| Macro | Meaning | Execution Behavior |
|---|---|---|
#DMS |
Validate proposal logic. | Analyze and validate the structural soundness against constraints before execution. |
#OTS |
Permit proactive improvements. | Permit clean-code optimizations or superior algorithmic patterns beyond the initial prompt. |
#FIX |
Execute all identified corrections. | Apply proposed non-destructive fixes immediately. |
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.
- yesterday First seen · 33 lines · 375 tokens per session scan C 527cbc5175ab
ai-instructions copilot-instructions.md is an instructions file published in the GitHub repository lsampaioweb/ai-instructions (1 stars, last pushed 12d ago), licensed MIT. It adds 375 tokens to every session, about $0.0019 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).