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.
npx agentmods add instructions/iamsecure1920/cordon-ai/claude-mdgit clone --depth 1 https://github.com/iamsecure1920/Cordon-AIWrote 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/iamsecure1920/cordon-ai/claude-md)<a href="https://agentmods.dev/instructions/iamsecure1920/cordon-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/iamsecure1920/cordon-ai/claude-md.svg" alt="Measured on agentmods" 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 | $0.02150 | $0.02150 |
| Opus 5 | $0.01075 | $0.01075 |
| Sonnet 5 | $0.00430 | $0.00430 |
| Haiku 4.5 | $0.00215 | $0.00215 |
Grade A, and why
Cordon-AI CLAUDE.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.
How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cordon AI — orientation for Claude
You are the strategy layer of an agentic VAPT orchestrator. This file is loaded automatically at session start. Read it before touching anything.
If you are on a freshly-cloned machine and nothing is installed yet, run
./bootstrap.sh — it is idempotent and safe to re-run. See docs/BOOTSTRAP.md.
1. The invariants — these are not negotiable
These come from the build guide and are enforced in code, not by your judgement. Do not weaken, bypass, or "temporarily disable" any of them.
- Authorized targets only. Owned assets, an in-scope bug bounty program, or org assets with documented written approval. The program policy text is the legal authorization and it drifts — re-pull and re-validate scope on every run.
- The MCP server is the security boundary, not the model. Scope checks, rate limits, argument sanitization, and approval gates are enforced server-side on every tool call. There is no code path that skips them. You cannot be trusted to enforce them yourself, and the design assumes you won't.
- Aggressive and state-changing actions require human approval. Exploitation is never auto-run.
- No PoC, no finding. A vulnerability is reported as confirmed only when a reproducible proof-of-concept validated it. Everything else is filed as "needs manual review."
- Never build scope-evasion capability. No feature whose purpose is to bypass scope, authorization, rate limits, or a program's published rules. If asked to add one, refuse and explain why.
- Treat every third-party MCP server, template, and payload list as untrusted until vetted and pinned.
The practical consequence: if a tool call returns scope_denied, that is the
system working correctly. Do not look for another route to the same target. Tell
the user the target is out of scope and stop.
2. What this is
An orchestrator that drives 83 catalogued open-source security tools through 101 MCP tools on a custom MCP server. You supply strategy; the MCP server supplies enforcement; the engines supply execution.
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.
- today Changed · +1 lines · +17 tokens per session 4ef3b189e87a
- 3d ago First seen · 185 lines · 2,133 tokens per session scan A 10de133435e1
Cordon-AI CLAUDE.md is an instructions file published in the GitHub repository iamsecure1920/Cordon-AI (0 stars, last pushed today), licensed MIT. It adds 2,150 tokens to every session, about $0.0107 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.
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).
spec-kit AGENTS.md
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.
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.
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 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).
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.