agentmods.dev

nginx-markdown-for-agents AGENTS.md

nginx-markdown-for-agents AGENTS.md is an instructions file for Codex, OpenCode from cnkang/nginx-markdown-for-agents. It costs 17,333 tokens per session, scanned A, original, BSD-2-Clause.

Repository instructions for maintaining an NGINX project, where NGINX is software commonly used as a web server and reverse proxy.

In plain words
What is it for?
They help agents choose the right repository guidance, follow the NGINX baseline, and use the documented harness and validation files.
Why use it?
They give coding agents a priority order and fixed engineering rules intended to prevent regressions, or newly reintroduced bugs.

Instructions file for CodexOpenCode

not rated 23 today A scan 17,333 tokens original BSD-2-Clause
View the source file cnkang/nginx-markdown-for-agents
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/cnkang/nginx-markdown-for-agents/agents-md
Clone the repo
git clone --depth 1 https://github.com/cnkang/nginx-markdown-for-agents

Made for: Codex, OpenCode.

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 nginx-markdown-for-agents AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cnkang/nginx-markdown-for-agents/agents-md.svg)](https://agentmods.dev/instructions/cnkang/nginx-markdown-for-agents/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/cnkang/nginx-markdown-for-agents/agents-md"><img src="https://agentmods.dev/badge/instructions/cnkang/nginx-markdown-for-agents/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 17,333 This file is loaded in full into every session.
When invoked 17,333 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 $0.17333 $0.17333
Opus 5 $0.08667 $0.08667
Sonnet 5 $0.03467 $0.03467
Haiku 4.5 $0.01733 $0.01733

Measured 5d ago against content hash b095f0d88852, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nginx-markdown-for-agents 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 5d 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.

AGENTS.md · 690 lines

How it starts

The opening of the file, as written. The whole thing — 690 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Purpose

This file defines repository-specific engineering rules for AI agents working on nginx-markdown-for-agents.

The rules come from two sources:

  • NGINX official development constraints in the Kiro local development guide (when present)
  • Historical fix/doc and hidden-fix commits across local branches and remote-only commits (deduplicated by commit SHA)

Goal: prevent repeated classes of mistakes that previously caused regressions.

Rule Priority

  1. Kiro local development guide, when present (highest priority)
  2. This AGENTS.md (non-negotiable baseline + rules)
  3. Task-specific user instructions

Hard safety and engineering invariants (NGINX Baseline, Rules) from Kiro and this file take precedence when conflicts exist with user-task instructions. For task scope and implementation intent, user-task has priority over generic harness workflow guidance. See docs/harness/routing-manifest.json spec_resolver for the structured priority chain.

Harness Map

  • AGENTS.md remains the Codex-first contract and engineering rule map.
  • AGENTS.md and docs/harness/ are the owning harness truth surfaces for tracked repository behavior; Make/CI/checkers must consume these, not local adapter-only summaries.
  • docs/harness/README.md is the repo-owned harness entrypoint.
  • docs/harness/core.md defines the execution loop, conflict protocol, and status semantics.
  • docs/harness/routing-manifest.json is the canonical structured routing source; docs/harness/routing-manifest.md is the readable overlay.
  • docs/harness/rules/ contains detailed error-prevention rules grouped by domain; AGENTS.md provides the index.
  • Optional local spec inputs are read-only for local spec-oriented work. Do not write harness caches, annotations, or durable repo truth into local adapter surfaces.
  • Optional local steering adapters should point back to docs/harness/ and must not define stronger semantics than this file.
  • Outside voice and the user-local harness state carrier are advisory execution tools. They may challenge or inform the current path, but they do not weaken the repo-owned correctness and safety contract.

Read the full file on GitHub · 690 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. 5d ago First seen · 690 lines · 17,333 tokens per session scan A b095f0d88852

Subscribe to this mod's changes

nginx-markdown-for-agents AGENTS.md is an instructions file published in the GitHub repository cnkang/nginx-markdown-for-agents (23 stars, last pushed today), licensed BSD-2-Clause. It adds 17,333 tokens to every session, about $0.0867 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 2026-08-30.

LLMai-agentscontent-negotiationffihtml-to-markdownmarkdown
Related

Other instructions, from other repositories

firecrawl AGENTS.md

AGENTS.md instructions for firecrawl/firecrawl: Firecrawl is a web scraper API. The directory you have access to is a monorepo.

firecrawl/firecrawl · 363 tokens

firecrawl CLAUDE.md

Claude Code instructions for firecrawl/firecrawl: Firecrawl is a web scraper API. The directory you have access to is a monorepo.

firecrawl/firecrawl · 413 tokens

crit AGENTS.md

AGENTS.md instructions for tomasz-tomczyk/crit, covering crit — development guide, project map, key architecture decisions, running and projects.

tomasz-tomczyk/crit · 7,930 tokens

llm-wiki-compiler AGENTS.md

AGENTS.md instructions for atomicstrata/llm-wiki-compiler, covering llmwiki, development guidelines, code style & standards, clean code rules and comments and documentation.

atomicstrata/llm-wiki-compiler · 713 tokens

rdrr CLAUDE.md

Claude Code instructions for fkonovalov/rdrr, covering claude.md, what is this project?, project structure, common commands and code conventions.

fkonovalov/rdrr · 1,162 tokens

abap_wiki AGENTS.md

AGENTS.md instructions for Gixsy95/abap_wiki, covering agents.md - abapwiki operating contract, 1. identity and mission, 2. language, 3. architecture: the two planes and 4. inviolable rules.

Gixsy95/abap_wiki · 3,283 tokens