Codex-web CLAUDE.md

A repository-specific instruction file for bproject07/Codex-web. It points developers to AGENTS.md, which defines the project's rules, security boundaries, product requirements, and required checks.

In plain words
What is it for?
Use it before editing the repository to learn which files and workflows to follow, what validation is deferred to GitHub Actions, and which live-server actions require explicit permission.
Why use it?
It tells coding agents how to work in that repository without violating its operating rules or running forbidden local checks.

Instructions file

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/bproject07/codex-web/claude-md
Clone the repo
git clone --depth 1 https://github.com/bproject07/Codex-web
Per session 123 This file is loaded in full into every session.
When invoked 123 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 $0.00123 $0.00123
Opus 5 $0.00062 $0.00062
Sonnet 5 $0.00025 $0.00025
Haiku 4.5 $0.00012 $0.00012

Measured 2d ago against content hash 0ab0d678062c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Codex-web CLAUDE.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.

CLAUDE.md · 14 lines

What it actually says

Claude Code Instructions

Read and follow AGENTS.md before editing this repository. It is the authoritative operational contract and contains the product invariants, security boundaries, and required CI checks.

Do not run builds, compilers, tests, package scripts, or browser regressions locally. GitHub Actions is the validation environment for this repository. Make source and documentation changes locally and report validation as pending until the GitHub workflow completes.

Do not start, stop, restart, replace, or overwrite a live packaged server unless the user explicitly requests that exact runtime action.

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 · 14 lines · 123 tokens per session scan A 0ab0d678062c

Subscribe to this mod's changes

Codex-web CLAUDE.md is an instructions file published in the GitHub repository bproject07/Codex-web (2 stars, last pushed 11d ago), licensed MIT. It adds 123 tokens to every session, about $0.0006 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.