ai-agents security.instructions.md

ai-agents security.instructions.md is an instructions file for GitHub Copilot from rjmurillo/ai-agents. It costs 832 tokens per session, scanned A, original, MIT.

Security change rules covering reviews, evidence, secrets, pinned third-party automation, threat models, and test coverage.

In plain words
What is it for?
Use them when changing security code, workflows, hooks, benchmarks, or anything that adds attack surface.
Why use it?
They reduce supply-chain and security risks by requiring documented justification and checks for security-sensitive changes.

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/rjmurillo/ai-agents/security
Clone the repo
git clone --depth 1 https://github.com/rjmurillo/ai-agents

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 ai-agents security.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/security.svg)](https://agentmods.dev/instructions/rjmurillo/ai-agents/security)
Your own site
<a href="https://agentmods.dev/instructions/rjmurillo/ai-agents/security"><img src="https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/security.svg" alt="Measured on agentmods" height="20"></a>
Per session 832 This file is loaded in full into every session.
When invoked 832 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 $0.00832 $0.00832
Opus 5 $0.00416 $0.00416
Sonnet 5 $0.00166 $0.00166
Haiku 4.5 $0.00083 $0.00083

Measured today against content hash 00d4bcfbb533, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-agents security.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 today.

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.instructions.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security File Rules

These paths hold threat models, benchmarks, workflows, and hooks that protect the supply chain. Changes need evidence, not opinion.

MUST

  1. Security agent review. Changes MUST be reviewed by the security agent (or a human with equivalent authority) before merge. Security review is always-on and cannot be skipped.
  2. Evidence-based. Every change MUST cite a CVE, CWE, OWASP reference, ADR, or documented threat. No speculative hardening.
  3. No secrets. MUST NOT commit credentials, tokens, signing keys, or API keys. Use the configured secrets manager.
  4. Pin Actions to SHA. Workflow changes MUST pin every third-party Action to a commit SHA. Floating tags (@v4, @main) are prohibited.
  5. Threat model updates. Changes that introduce new attack surface MUST update the relevant benchmark under .agents/security/benchmarks/ or cite why no update is required.
  6. Test coverage. Security-critical code MUST have 100% coverage per AGENTS.md standards.
  7. Eureka: gate availability is gate correctness. A required security review that does not run MUST produce a blocking verdict. Infrastructure failure is not a security pass. Issue #4777 records the failure where ten missing reviews produced a green required check.

SHOULD

  1. Run security scan locally. SHOULD run the security-scan skill (.claude/skills/security-scan/scripts/scan_vulnerabilities.py) before pushing. The internal scanner detects CWE-78 (command injection) only; CWE-22 (path traversal) detection is delegated to CodeQL in CI per ADR-054 amendment 2026-05-02.
  2. Use the security-detection skill. SHOULD detect security-relevant file changes via the skill and route to the security agent.
  3. Threat modeling. SHOULD use the threat-modeling skill (OWASP STRIDE) for non-trivial changes.

MUST NOT

  1. MUST NOT lower severity thresholds in SECURITY-SEVERITY-CRITERIA.md without governance ADR.
  2. MUST NOT skip security checks in CI.
  3. MUST NOT merge security-sensitive changes without explicit approval, even when auto-merge labels are applied.

Read the full file on GitHub · 42 lines

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. today First seen · 42 lines · 832 tokens per session scan A 00d4bcfbb533

Subscribe to this mod's changes

ai-agents security.instructions.md is an instructions file published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 832 tokens to every session, about $0.0042 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 2026-09-03.