copilot-security-instructions security-library-authoring.instructions.md

copilot-security-instructions security-library-authoring.instructions.md is an instructions file for GitHub Copilot from Robotti-io/copilot-security-instructions. It costs 369 tokens per session, scanned A, original, Apache-2.0.

A set of writing rules for creating security-focused prompts, skills, and agents in a code repository. It is intended for AppSec, the practice of finding and preventing software security problems early.

In plain words
What is it for?
Creating security prompts, skills, and agents with required sections, evidence, severity, remediation, and verification steps. It also helps check that these files use the required metadata and structure.
Why use it?
It makes security reviews repeatable and evidence-based, while discouraging unsafe quick fixes. It also gives findings a consistent format that can be copied into issues or pull requests.

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/robotti-io/copilot-security-instructions/security-library-authoring
Clone the repo
git clone --depth 1 https://github.com/Robotti-io/copilot-security-instructions

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for copilot-security-instructions security-library-authoring.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/robotti-io/copilot-security-instructions/security-library-authoring.svg)](https://agentmods.dev/instructions/robotti-io/copilot-security-instructions/security-library-authoring)
Your own site
<a href="https://agentmods.dev/instructions/robotti-io/copilot-security-instructions/security-library-authoring"><img src="https://agentmods.dev/badge/instructions/robotti-io/copilot-security-instructions/security-library-authoring.svg" alt="Measured on agentmods" height="20"></a>
Per session 369 This file is loaded in full into every session.
When invoked 369 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 5.1 $0.00369 $0.00369
Opus 5 $0.00185 $0.00185
Sonnet 5 $0.00074 $0.00074
Haiku 4.5 $0.00037 $0.00037

Measured 5d ago against content hash 3cab80056f41, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

copilot-security-instructions security-library-authoring.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 5d 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/security-library-authoring.instructions.md · 54 lines

What it actually says

Security library authoring rules (this repo)

These rules apply to the root-level library content intended for AppSec “shift-left” use.

Global requirements

  • Prefer deterministic, repeatable workflows.
  • Always require evidence:
    • reference exact file paths and (when possible) line ranges
    • avoid speculative conclusions
  • Avoid insecure “quick fixes”:
    • do not recommend disabling security controls as the primary solution
    • if a risky workaround is mentioned, it must be explicitly labeled temporary with safer alternatives

Root prompt files: prompts/*.prompt.md

  • MUST include these sections:
    • ## ✅ Context / Assumptions
    • ## 🔍 Procedure
    • ## 📦 Output Format
    • ## ✅ Quality checks
  • MUST define an output schema that is easy to paste into issues/PRs:
    • Findings list/table
    • Severity / likelihood
    • Evidence
    • Remediation
    • Verification steps

Skills: skills/**/SKILL.md

  • MUST include YAML frontmatter with name and description.
  • MUST include:
    • When to use
    • Inputs to collect
    • Step-by-step process
    • Output format
    • Examples

Agents: agents/*.agent.md

  • MUST include YAML frontmatter with description.
  • MUST define:
    • operating principles
    • how to handle missing info
    • output format expectations (findings, fixes, verification)

README

  • Prompt catalogue SHOULD include every file in prompts/ with a one-line description and intended use.
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. 5d ago First seen · 54 lines · 369 tokens per session scan A 3cab80056f41

Subscribe to this mod's changes

copilot-security-instructions security-library-authoring.instructions.md is an instructions file published in the GitHub repository Robotti-io/copilot-security-instructions (42 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 369 tokens to every session, about $0.0018 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.