everything-ai-coding AGENTS.md

Repository instructions for AI coding agents working on a project that uses CLAUDE.md for its architecture and development conventions. They explain how to handle proposal files, tests, commits, and project context.

In plain words
What is it for?
Use them when making non-trivial changes, reading project guidance, adding tests, or preparing commits in the everything-ai-coding repository.
Why use it?
They keep temporary change proposals out of the repository and preserve the project’s existing rules for tracked and new test files. This reduces accidental commits and inconsistent changes.

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/zgsm-ai/everything-ai-coding/agents-md
Clone the repo
git clone --depth 1 https://github.com/zgsm-ai/everything-ai-coding

Made for: Codex, OpenCode.

Per session 405 This file is loaded in full into every session.
When invoked 405 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 $0.00405 $0.00405
Opus 5 $0.00202 $0.00202
Sonnet 5 $0.00081 $0.00081
Haiku 4.5 $0.00040 $0.00040

Measured yesterday against content hash d8e94190c512, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

everything-ai-coding 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 yesterday.

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 · 28 lines

What it actually says

AGENTS.md

Operating guidance for AI coding agents (Claude Code / Codex / Cursor / Opencode / Costrict / etc.) working in this repo.

Project context

See CLAUDE.md for the architectural overview, commit conventions, test commands, and the data pipeline. Read it before making any non-trivial change.

Do not commit openspec/

openspec/changes/<name>/ is a working directory for proposals, designs, and tasks. It is intentionally ignored (.gitignore:13 openspec/) and should not be pushed to origin/main.

  • When you scaffold a change with /opsx:propose or openspec new change, keep the resulting files local.
  • Do NOT use git add -f openspec/... to bypass .gitignore.
  • If you find tracked files under openspec/ on origin/main, untrack them with git rm --cached in a maintenance commit — those are historical leakage from before this rule.
  • The final spec ends up in code, tests, and CLAUDE.md. The change folder is a scratchpad, not the source of truth.

Test files

tests/ is also in .gitignore for historical reasons but a large set of files there are tracked (legacy state). When adding new tests:

  • For pre-existing tracked test files: edit normally, they pick up changes.
  • For brand-new test files: don't force-add — submit them as part of the change description / openspec change directory locally, so reviewers see the test coverage logic without polluting the tracked test surface. Production coverage that must run in CI should live under ai-resource-eval/tests/ instead.

Commit conventions

See CLAUDE.md § 提交规范. TL;DR: [type] 中文描述, single concern per commit, no Co-Authored-By unless explicitly collaborating.

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. yesterday First seen · 28 lines · 405 tokens per session scan A d8e94190c512

Subscribe to this mod's changes

everything-ai-coding AGENTS.md is an instructions file published in the GitHub repository zgsm-ai/everything-ai-coding (205 stars, last pushed 5d ago), licensed MIT. It adds 405 tokens to every session, about $0.0020 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.