Borrowing it
Nothing to install: this file belongs to paradigmxyz/iron-proxy. 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/paradigmxyz/iron-proxy/main/AGENTS.mdgit clone --depth 1 https://github.com/paradigmxyz/iron-proxyWrote 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/paradigmxyz/iron-proxy/agents-md)<a href="https://agentmods.dev/instructions/paradigmxyz/iron-proxy/agents-md"><img src="https://agentmods.dev/badge/instructions/paradigmxyz/iron-proxy/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/paradigmxyz/iron-proxy/agents-md"><img src="https://agentmods.dev/badge/instructions/paradigmxyz/iron-proxy/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 | $0.01429 | $0.01429 |
| Opus 5.5 | $0.00572 | $0.00572 |
| Sonnet 5.5 | $0.00286 | $0.00286 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade B, and why
iron-proxy AGENTS.md scanned grade B with 1 finding 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.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
`proxy.upstream_deny_cidrs` (loopback and `169.254.169.254` by default) Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working in this repo. Optimized for the review
and implementation flow used by /review, /security-review, and similar
tools.
Repo at a glance
- Single Go module:
github.com/ironsh/iron-proxy(Go 1.26+). - One binary:
cmd/iron-proxy(the MITM egress proxy). - Core packages live under
internal/. The transform pipeline lives ininternal/transform/with one subpackage per transform (allowlist,secrets,bodycapture,headerallowlist,annotate,judge,grpc,hmacsign,oauth,awsauth,gcpauth). - Integration tests against real backends (AWS, 1Password, GCP, Postgres,
gRPC, MCP) live in
integration_test/. Unit tests sit next to the code they exercise.
The README is the source of truth for product behavior. When in doubt about intended behavior, read it before changing code.
Go conventions
- Use
github.com/stretchr/testify/requirefor assertions. Nevert.Errorf/t.Fatalffor value comparisons whenrequire.Equalwould do. - Table-driven tests are the default for any function with more than two
meaningful input shapes. Name the table
casesortests, iterate witht.Run(tc.name, ...). require.NoError(err)on every error returned from a function under test. Never silently ignore errors. In tests, the only acceptable place to drop an error is inside a background goroutine (e.g. an HTTP handler) and it must use_with a comment explaining why the error is unreachable or irrelevant.- Production code: never silently swallow errors. If an error truly cannot
occur, suppress with
_and a one-line comment stating why. - Respect
context.Contexton every network or I/O call. Background goroutines need an explicit lifecycle (shutdown channel, context, or errgroup). - Prefer the standard library and the existing dependencies in
go.modover adding new ones.
Simplicity
- Aim for the smallest change that solves the problem. Don't add features, abstractions, or configuration knobs the task didn't ask for.
- Don't design for hypothetical future requirements. Two similar code blocks are fine; if the same shape appears a third time, factor a helper and update the call sites in the same change.
- Prefer deleting code over adding it. If a refactor leaves dead branches, unused config fields, or backwards-compat shims behind, remove them.
- No premature interfaces. Introduce an interface when a second concrete implementation actually exists, not in anticipation of one.
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 First seen · 131 lines · 1,429 tokens per session scan B 6a1f81effb89
iron-proxy AGENTS.md is an instructions file published in the GitHub repository paradigmxyz/iron-proxy (829 stars, last pushed 6d ago), licensed Apache-2.0. It adds 1,429 tokens to every session, about $0.0057 per session on Opus 5.5. A static security scan graded it B with 1 finding (cloud metadata endpoint). 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.