agentops-config-toolkit copilot-instructions.md

A set of project instructions for GitHub Copilot, an AI coding assistant. It defines how the assistant should inspect files, make changes, and format replies.

In plain words
What is it for?
Use it to guide Copilot during software changes, especially when you want small patches, preserved behavior, concise responses, and clear handling of uncertainty.
Why use it?
It keeps coding work focused and reduces unnecessary rewrites, output, and exploration. It also tells Copilot which generated or bulky files to skip.

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/stealthsrc/agentops-config-toolkit/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/stealthsrc/agentops-config-toolkit

Made for: GitHub Copilot.

Per session 385 This file is loaded in full into every session.
When invoked 385 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 $0.00385 $0.00385
Opus 5 $0.00192 $0.00192
Sonnet 5 $0.00077 $0.00077
Haiku 4.5 $0.00038 $0.00038

Measured yesterday against content hash 0f69968ef4b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentops-config-toolkit 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 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.

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-copilot/.github/copilot-instructions.md · 39 lines

What it actually says

GitHub Copilot project instructions

Minimize tokens, scope, and output.

Core rules

  1. Smallest correct change. No broad rewrites.
  2. Read only directly relevant files, tools, docs, and context. No broad exploration.
  3. Preserve existing APIs, behavior, and conventions.
  4. Prefer short Markdown or prose. Use JSON, YAML, or XML only if requested or machine-required.
  5. Summarize noisy output with errors, warnings, changed paths, and counts. Collapse passes and repeated lines unless raw output is requested.
  6. Prefer minimal patches or diffs over full-file rewrites.
  7. Keep reasoning internal. Return only what completes the task.
  8. Surface ambiguity. Ask only if blocking.
  9. Ignore: node_modules/, dist/, build/, .next/, coverage/, vendor/, target/, lockfiles, generated code, minified assets, binaries, large logs/snapshots.
  10. Match existing style even if you'd write it differently.
  11. Mention dead code or issues outside scope. Don't fix them.

Before coding

  • Non-trivial task -> state brief plan + verifiable success criteria.
  • Multiple valid interpretations -> list them, pick one or ask.
  • Simpler approach available -> say so before implementing.

Response format

  • Answer - direct result
  • Cause - root cause, 1 line (if diagnosing)
  • Files - paths only (if files touched)
  • Fix - what changed, 1-3 lines (if change made)
  • Validation - exact command/route + expected (if verifiable)

No preamble. No task restatement. No optional suggestions.

Reminder

Smallest change. Fewest files. Shortest output. Stop at first correct solution. No alternatives. No preamble.

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. yesterday First seen · 39 lines · 385 tokens per session scan A 0f69968ef4b9

Subscribe to this mod's changes

agentops-config-toolkit copilot-instructions.md is an instructions file published in the GitHub repository stealthsrc/agentops-config-toolkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 385 tokens to every session, about $0.0019 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.