agentrig security.instructions.md

Project-wide security instructions for editing code in an agentic software harness, a system that coordinates other automated coding tools.

In plain words
What is it for?
Use them on every code edit to guide secret handling, input validation, safe database and shell usage, output escaping, dependency choices, and review of authentication or cryptography changes.
Why use it?
They reduce common risks such as leaked secrets, unsafe input handling, injection attacks, excessive permissions, and disabled security checks.

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/doidor/agentrig/security
Clone the repo
git clone --depth 1 https://github.com/doidor/agentrig

Made for: GitHub Copilot.

Per session 293 This file is loaded in full into every session.
When invoked 293 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 $0.00293 $0.00293
Opus 5 $0.00147 $0.00147
Sonnet 5 $0.00059 $0.00059
Haiku 4.5 $0.00029 $0.00029

Measured yesterday against content hash c34081babcae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentrig 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 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/instructions/security.instructions.md · 23 lines

What it actually says

Security rules (reflex)

Apply on every edit. When in doubt, stop and flag rather than guess.

  • No secrets in source. Never commit tokens, keys, passwords, or connection strings. Read them from environment/secret stores. If you spot a committed secret, stop and report it.
  • Validate and sanitize all external input (request bodies, query params, CLI args, file contents, env). Reject/normalize before use.
  • No injection. Use parameterized queries; never string-concatenate SQL/shell/HTML from input. Avoid eval, dynamic require, and shelling out with unsanitized input.
  • Escape on output to prevent XSS; use the framework's escaping, not hand-rolled.
  • Least privilege. Don't broaden file, network, or token scopes to make something work.
  • Don't disable security controls (auth checks, CSRF, TLS verification, lint security rules) to pass a test or unblock a build.
  • Dependencies: prefer maintained, pinned versions; don't add a dependency to avoid a few lines.

If a change touches auth, crypto, or input boundaries, call it out explicitly for review.

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 · 23 lines · 293 tokens per session scan A c34081babcae

Subscribe to this mod's changes

agentrig security.instructions.md is an instructions file published in the GitHub repository doidor/agentrig (5 stars, last pushed 1mo ago), licensed MIT. It adds 293 tokens to every session, about $0.0015 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.

Related

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.

openai/codex · 5,182 tokens

buildNext

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).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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).

microsoft/vscode · 5,001 tokens

spec-kit 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.

github/spec-kit · 7,040 tokens

langchain 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.

langchain-ai/langchain · 4,345 tokens