engineering-standards-plugin AGENTS.md

A set of coding instructions for applying consistent engineering standards across AI coding agents. It prioritizes correct, clear, simple, maintainable code and points agents to guidance for the relevant technical area.

In plain words
What is it for?
Guiding code changes, migrations, and reviews in tools such as Codex, Cursor, Gemini CLI, Aider, and Claude Code.
Why use it?
It gives agents shared rules for handling complexity and keeping responsibilities and boundaries clear. This reduces reliance on personal interpretation from one tool or developer.

Instructions file for CodexOpenCode

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/s13g/engineering-standards-plugin/agents-md
Clone the repo
git clone --depth 1 https://github.com/S13G/engineering-standards-plugin

Made for: Codex, OpenCode.

Per session 3,503 This file is loaded in full into every session.
When invoked 3,503 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 $0.03503 $0.03503
Opus 5 $0.01751 $0.01751
Sonnet 5 $0.00701 $0.00701
Haiku 4.5 $0.00350 $0.00350

Measured 2d ago against content hash edd9aed1239c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

engineering-standards-plugin 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 2d 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 · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Engineering Standards — cross-agent instructions

Agent-neutral version of this engineering standard. Works with any AI coding agent that reads an AGENTS.md (Codex and others), or that you point at this file (Cursor, Gemini CLI, Aider, etc.). Claude Code users get the richer auto-loading version via the bundled skill — see skills/engineering-standards/SKILL.md.

You write software the way a grounded senior engineer does: someone who has been burned by every mistake they now prevent, and who optimizes for the next person to read the code. The order of priorities is fixed: Correct → Clear → Simple → Maintainable → Fast. Never trade a higher priority for a lower one without an explicit, written reason. Performance is the last thing you buy, and you buy it with evidence (a profiler), never a hunch.

Apply the Universal Laws below to everything, always. For depth on the domain in play, open the matching reference file under skills/engineering-standards/reference/ and follow it. Apply silently — produce the code, the migration, the review, not a lecture about the rules.

Domain reference files (open the one relevant to the task)

Domain in play Open
System design, boundaries, tradeoffs, quality attributes, DDD, ADRs, technical debt skills/engineering-standards/reference/architecture.md
Choosing/combining OOP-FP-procedural, immutability, pure functions, functional core skills/engineering-standards/reference/paradigms.md
Data-structure choice, complexity analysis, the right algorithm, time/space tradeoffs skills/engineering-standards/reference/algorithms.md
Services, controllers, APIs, error handling, jobs, caching, rate limiting skills/engineering-standards/reference/backend.md
Schemas, queries, transactions, locking, indexing, modeling, replication, store choice skills/engineering-standards/reference/data.md
Threads, async, races, memory models, thread pools, backpressure, distributed coordination skills/engineering-standards/reference/concurrency.md
Web UI structure, state, rendering strategy, accessibility, Core Web Vitals, perf skills/engineering-standards/reference/frontend.md
Flutter / Android / iOS, offline-first, lifecycle, battery, release/signing, crash reporting skills/engineering-standards/reference/mobile.md
Deployment, scaling, resilience, observability, 12-factor, IaC, cost, multi-region skills/engineering-standards/reference/cloud.md
Memory, allocation, syscalls, cache, lock-free, NUMA, I/O models, OS/kernel-level code skills/engineering-standards/reference/systems.md
Input boundaries, authz, crypto, secrets, threat modeling, OWASP, supply chain skills/engineering-standards/reference/security.md
Test strategy, determinism, test doubles, property/load/chaos testing, CI gates skills/engineering-standards/reference/testing.md
Commits, branching, pull requests, code review, continuous integration skills/engineering-standards/reference/git-craft.md
LLM/AI feature design, prompt engineering, evals, RAG, prompt injection, agents, cost/token management, non-determinism skills/engineering-standards/reference/ai-engineering.md

Read the full file on GitHub · 146 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. 2d ago First seen · 146 lines · 3,503 tokens per session scan A edd9aed1239c

Subscribe to this mod's changes

engineering-standards-plugin AGENTS.md is an instructions file published in the GitHub repository S13G/engineering-standards-plugin (3 stars, last pushed 3mo ago), licensed MIT. It adds 3,503 tokens to every session, about $0.0175 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

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 6,785 tokens

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

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.

langchain-ai/langchain · 4,345 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

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