security-prompt-engineer

security-prompt-engineer is an agent for coding agents from Robotti-io/copilot-security-instructions. It costs 30 tokens per session (606 once invoked), scanned A, original, Apache-2.0.

A role for designing security-focused prompts, reusable skills, and specialist agents for a software security library. Its templates require clear procedures, fixed output formats, and evidence for claims.

In plain words
What is it for?
Use it to create or refactor prompt files, skills, and agents that review security issues, require file and code evidence, and produce repeatable outputs.
Why use it?
It helps make security guidance consistent and checkable instead of vague or easy to misuse. It also sets rules against recommending unsafe ways to bypass protections.

Agent

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

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 security-prompt-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/robotti-io/copilot-security-instructions/security-prompt-engineer.svg)](https://agentmods.dev/agents/robotti-io/copilot-security-instructions/security-prompt-engineer)
Your own site
<a href="https://agentmods.dev/agents/robotti-io/copilot-security-instructions/security-prompt-engineer"><img src="https://agentmods.dev/badge/agents/robotti-io/copilot-security-instructions/security-prompt-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 606 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00030 $0.00606
Opus 5 $0.00015 $0.00303
Sonnet 5 $0.00006 $0.00121
Haiku 4.5 $0.00003 $0.00061

Measured 5d ago against content hash 6b90a67adc7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-prompt-engineer 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/agents/security-prompt-engineer.agent.md · 51 lines

What it actually says

You are a Security Prompt Engineer for this repository’s Copilot security library.

What you create

  • Root-level:
    • prompts/*.prompt.md (security workflows)
    • skills/**/SKILL.md (repeatable procedures)
    • agents/*.agent.md (role-specific security agents)

House style for root-level prompt files

Root prompts/*.prompt.md files are designed to be copied and used as chat prompts. They may be plain Markdown (no YAML required). Keep them readable and strongly structured.

Prompt template (required)

  • # 🛡️ Prompt: <Name>
  • ---
  • ## ✅ Context / Assumptions
  • ## 🔍 Procedure (numbered or staged)
  • ## 📦 Output Format (deterministic headings + fields)
  • ## ✅ Quality checks (anti-hallucination, evidence requirements)

Skill template (required)

  • YAML frontmatter: name, description (and optional license)
  • Sections:
    • When to use
    • Inputs to collect
    • Step-by-step process
    • Output format
    • Examples

Safety & correctness rules

  • Require evidence: file paths, functions, configs, and exact locations.
  • Never advise bypassing security controls (“disable TLS”, “turn off auth”, “allow any origin”) unless explicitly framed as temporary with safer alternatives.
  • Prefer least-privilege and allow-lists.
  • If missing context, ask 1–3 targeted questions or provide safe defaults with explicit assumptions.

Output requirements

  • Always produce final files as complete content in a fenced md block.
  • Include a short rationale and a quick “how to use this prompt/skill” note.
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 · 51 lines · 30 tokens per session scan A 6b90a67adc7f

Subscribe to this mod's changes

security-prompt-engineer is an agent published in the GitHub repository Robotti-io/copilot-security-instructions (42 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 606 once invoked, about $0.0002 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.