Borrowing it
Nothing to install: this file belongs to SquidSec/SquidC5. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/SquidSec/SquidC5/master/AGENTS.mdgit clone --depth 1 https://github.com/SquidSec/SquidC5Wrote 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.
[](https://agentmods.dev/instructions/squidsec/squidc5/agents-md)<a href="https://agentmods.dev/instructions/squidsec/squidc5/agents-md"><img src="https://agentmods.dev/badge/instructions/squidsec/squidc5/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/squidsec/squidc5/agents-md"><img src="https://agentmods.dev/badge/instructions/squidsec/squidc5/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.05479 | $0.05479 |
| Opus 5.5 | $0.02192 | $0.02192 |
| Sonnet 5.5 | $0.01096 | $0.01096 |
| Haiku 4.5 | $0.00548 | $0.00548 |
Grade A, and why
SquidC5 AGENTS.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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 445 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Instructions for AI Agents Working on SquidC5
Classification & Mission
SquidC5 is a military-grade, security-first, AI-native C5 platform - Command - Control - Cognitive - Collaborative - Coordination - under active development for authorized red team, penetration testing, and defensive security operations only.
Treat every change as if the system will be deployed in high-threat environments:
- Prefer secure defaults over convenience
- Minimize attack surface and fingerprinting
- Never weaken auth, AI sandboxing, audit, or allow-lists without explicit human design review
- Assume hostile network exposure (internet-facing listeners, scanners, credential stuffing)
Unauthorized access assistance is out of scope. Do not help with illegal use.
Project Stack
Primary language: Python 3.11+ - FastAPI - SQLite - Docker-first
Operator CLI: sc5 (also squidc5-cli)
Ops UI: /ops (admin UI loaded only after server-side admin token check)
Non-Negotiable Security Rules
- Secure by default: New installs must ship hardened (no public docs/OpenAPI, no wildcard CORS, MCP off until enabled, exec probe on, false-shell filter on).
- External AI restriction: MCP tools must remain allow-listed per token. No open-ended autonomous agent loops for external models.
- Admin AI / INKO shielding: Never feed raw session output into LLM prompts without
sanitize_untrusted(). Keep capabilities and chat tools allow-listed. Prefer offline/deterministic fallbacks when no LLM is configured. No open-ended autonomous agent loops. - Determinism preference: Templates, fixed prompts, single-step tools over free-form agentic planning.
- Audit everything: Operator, MCP, Admin AI, feature toggles, and admin UI loads go through the policy engine / audit trail.
- No secrets in git: Tokens, API keys,
data/,admin_token.txt,~/.config/squidc5/config.jsonstay out of the repository. - Port flexibility: Never hard-require ports 80 or 443 - operators may use them.
- Admin UI isolation: Admin-only HTML/JS must be served only after server validates an admin token (
/api/v1/ops/admin.js). Non-admin clients must never receive admin control code. - Public docs locked off:
/docs,/redoc,/openapi.jsonstay disabled. Feature flagpublic_docsis hard-forcedfalse. - Authorized use only.
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.
- 1mo ago Changed · +2 lines · +57 tokens per session 4aa3c7dcf0cd
- 1mo ago Changed · +11 lines · +180 tokens per session 88672415b8a6
- 1mo ago First seen · 432 lines · 5,242 tokens per session scan A 4964ce9ca24d
SquidC5 AGENTS.md is an instructions file published in the GitHub repository SquidSec/SquidC5 (57 stars, last pushed 4d ago), licensed MIT. It adds 5,479 tokens to every session, about $0.0219 per session on Opus 5.5. 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.