agentmods.dev

codex-as AGENTS.md

Repository instructions for codex-as, a small Bash wrapper that launches Codex with selected authentication or provider profiles.

In plain words
What is it for?
Use them when changing the wrapper, authentication backends, shell completions, multilingual README files, dependency instructions, or its verification tests.
Why use it?
They preserve per-process authentication settings and prevent changes from permanently altering the user’s global Codex configuration.

Instructions file for CodexOpenCode

2 2mo ago B scan 296 tokens original MIT
View the source file Axiweave/codex-as
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/axiweave/codex-as/agents-md
Clone the repo
git clone --depth 1 https://github.com/Axiweave/codex-as

Made for: Codex, OpenCode.

Per session 296 This file is loaded in full into every session.
When invoked 296 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.00296 $0.00296
Opus 5 $0.00148 $0.00148
Sonnet 5 $0.00059 $0.00059
Haiku 4.5 $0.00030 $0.00030

Measured 2d ago against content hash ef20ae541bcf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

codex-as 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Prefer `codex -c` runtime overrides over editing `~/.codex/config.toml`.
AGENTS.md · 35 lines

What it actually says

AGENTS.md

Project Scope

This repository contains codex-as, a small Bash wrapper for launching Codex with selected auth/provider profiles.

Development Notes

  • Keep the implementation small and shell-first.
  • Do not commit downloaded reference repos under refs/; they are local research material.
  • Do not commit docs/superpowers/; keep those files local if generated.
  • Prefer codex -c runtime overrides over editing ~/.codex/config.toml.
  • Preserve the core design goal: avoid permanent global mutation of ~/.codex/auth.json and ~/.codex/config.toml.
  • On Linux, prefer the bubblewrap backend for per-process auth substitution.
  • On macOS, keep the startup-window fallback as the default and session-lock mode as the stricter opt-in behavior.
  • When changing user-facing README content, update all language variants: README.md, README.zh-CN.md, and README.zh-TW.md.
  • Keep dependency and install instructions synchronized across all README language variants, including bubblewrap package install commands.

Verification

Before publishing changes, run:

test/codex-as-test.bash
shellcheck bin/codex bin/codex-as test/codex-as-test.bash
zsh -n completions/_codex-as
git diff --check
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 · 35 lines · 296 tokens per session scan B ef20ae541bcf

Subscribe to this mod's changes

codex-as AGENTS.md is an instructions file published in the GitHub repository Axiweave/codex-as (2 stars, last pushed 2mo ago), licensed MIT. It adds 296 tokens to every session, about $0.0015 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

account-switcherauthbashbubblewrapclicodex
Related

Other instructions, from other repositories

codex-profiles AGENTS.md

Instructions for Ducksss/codex-profiles, covering agents.md, what this project is, repository layout, setup, build, and test and how to run the tool.

Ducksss/codex-profiles · 1,560 tokens

headson CLAUDE.md

Instructions for kantord/headson, covering headson — agents guide, mission, primary surfaces to mind, core pipeline (keep behaviors intact) and heuristics & semantics to preserve.

kantord/headson · 1,357 tokens

ralph CLAUDE.md

Instructions for SantanderAI/ralph, covering ralph — instrucciones del proyecto and paridad bash ↔ powershell (importante).

SantanderAI/ralph · 254 tokens

claude-code-statusline CLAUDE.md

Instructions for glauberlima/claude-code-statusline, covering claude.md, project overview, development commands, testing and run all tests (unit + integration).

glauberlima/claude-code-statusline · 2,776 tokens

auto-uv-env AGENTS.md

Instructions for ashwch/auto-uv-env, covering agents.md - the auto-uv-env story, what this repo is, architecture diagrams, runtime activation flow and repository lifecycle.

ashwch/auto-uv-env · 3,245 tokens

nightdev_rep AGENTS.md

Instructions for hiramgabriel1/nightdev_rep, covering agents.md, commands, architecture, key conventions and git workflow.

hiramgabriel1/nightdev_rep · 357 tokens