What is codexm AGENTS.md?

A repository instruction file named AGENTS.md for a Go command-line application. It documents the project layout, development commands, coding expectations, and testing guidance.

It guides work on the command-line interface, configuration, Codex integration, shared tool configuration, scripts, documentation, builds, tests, formatting, and static analysis.

It gives coding agents the project-specific information needed to build, test, format, and review changes consistently.

codexm AGENTS.md — Instructions file by iamcc30

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/iamcc30/codexm/agents-md

Clone the repo

git clone --depth 1 https://github.com/iamcc30/codexm

Made for: Codex, OpenCode.

Per session 612 This file is loaded in full into every session.

When invoked 612 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.

Model	Per session	Once invoked
Fable 5	$0.00612	$0.00612
Opus 5	$0.00306	$0.00306
Sonnet 5	$0.00122	$0.00122
Haiku 4.5	$0.00061	$0.00061

Measured yesterday against content hash 0f8c3aa60fd2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codexm 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 · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

codexm is a Go 1.22 command-line application. The executable entry point is cmd/codexm/main.go. Core packages live under internal/: cli parses commands, config manages profiles and project bindings, codex invokes the upstream Codex CLI, and sharedmcp synchronizes MCP configuration. Tests sit beside their packages as *_test.go. Shell and PowerShell helpers are in scripts/; cross-platform release automation lives in .github/workflows/release.yml. User-facing documentation is maintained in both README.md and README.zh-CN.md. Generated binaries and archives belong in bin/ or dist/ and must not be committed.

Build, Test, and Development Commands

go build -o codexm ./cmd/codexm builds a local executable.
go test ./... runs all package tests.
go vet ./... performs standard Go static analysis.
go fmt ./... formats all Go sources.
./scripts/build-all.sh dev tests and creates archives for supported Linux, macOS, and Windows targets under dist/.

Run the formatter, tests, and vet before opening a pull request. The external codex executable is required for manual end-to-end CLI checks.

Coding Style & Naming Conventions

Follow idiomatic Go and let gofmt determine indentation and layout. Use short, lowercase package names; exported identifiers use PascalCase, unexported identifiers use camelCase. Keep command handlers consistent with the existing cmdXxx methods in internal/cli. Return errors with useful context, preserve wrapped causes where appropriate, and avoid exposing credentials or profile secrets in output.

Testing Guidelines

Use Go's standard testing package. Name tests TestBehaviorOrScenario and keep fixtures isolated with t.TempDir(). Add regression tests beside the changed package for bug fixes and cover both success and failure paths. There is no numeric coverage target; prioritize profile isolation, path resolution, configuration preservation, and idempotent synchronization behavior.

Read the full file on GitHub · 59 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.

yesterday First seen · 59 lines · 612 tokens per session scan A 0f8c3aa60fd2

Subscribe to this mod's changes

codexm AGENTS.md is an instructions file published in the GitHub repository iamcc30/codexm (1 stars, last pushed 1mo ago), licensed MIT. It adds 612 tokens to every session, about $0.0031 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.

Languages Testing Writing and docs account-manager account-switcher cli codex codex-cli codex-skills

codexm AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Repository Guidelines

Project Structure & Module Organization

Build, Test, and Development Commands

Coding Style & Naming Conventions

Testing Guidelines

What this file has done since we first saw it

Other instructions, from other repositories

skills AGENTS.md

dev-flow AGENTS.md

delegate-to-deepseek-harness AGENTS.md

codex-switch AGENTS.md

skills CLAUDE.md

scodex AGENTS.md