codex

A guide for connecting Codex, an AI software-development agent, to Bulwark, an HTTP proxy that controls and records requests to outside services.

In plain words
What is it for?
Use it when Codex needs to access services such as GitHub, Slack, or AWS through Bulwark's proxy, including HTTPS inspection when configured.
Why use it?
It adds a central place to enforce API access rules, provide credentials, inspect content, record requests, and limit traffic or costs.

Agent

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 agents/claudius-ars/bulwark/codex
Clone the repo
git clone --depth 1 https://github.com/claudius-ars/bulwark
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,890 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 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 $0.00000 $0.04890
Opus 5 $0.00000 $0.02445
Sonnet 5 $0.00000 $0.00978
Haiku 4.5 $0.00000 $0.00489

Measured yesterday against content hash f56debf0f9c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex scanned grade A with 2 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.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

# macOS: sudo security add-trusted-cert -d -r trustRoot -k /Library/Keychains/System.keychain ~/.bulwark/ca/bulwark-ca.crt

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

3. Test proxy directly: `curl -x http://localhost:8080 https://api.github.com`
docs/agents/codex.md · 763 lines

How it starts

The opening of the file, as written. The whole thing — 763 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Integration

Codex is an AI agent for software development that operates through HTTP APIs. Bulwark integrates with Codex via the HTTP forward proxy to add governance, policy enforcement, and audit logging.

Overview

Bulwark provides Codex with:

  • Policy enforcement: Control which APIs Codex can access
  • Credential management: Securely inject API keys and tokens
  • Audit logging: Track all HTTP requests and decisions
  • Content inspection: Scan for secrets, PII, and security issues
  • Rate limiting: Control request rates and costs
  • TLS MITM: Inspect HTTPS traffic for governance

Architecture

Codex Agent
    |
    | (HTTP/HTTPS proxy)
    |
Bulwark HTTP Proxy
    |
    | (Policy, Credentials, Audit, Content Inspection)
    |
External APIs (GitHub, Slack, AWS, etc.)

Codex is configured to route all HTTP traffic through Bulwark's forward proxy, which enforces policies and injects credentials before forwarding to external APIs.

Configuration

1. Configure Bulwark HTTP Proxy

Create or edit ~/.bulwark/bulwark.yaml:

http:
  enabled: true
  listen_addr: "127.0.0.1:8080"

  # TLS MITM for HTTPS inspection
  tls:
    enabled: true
    ca_cert: ~/.bulwark/ca/bulwark-ca.crt
    ca_key: ~/.bulwark/ca/bulwark-ca.key

  # URL-to-tool mappings for policy enforcement
  tool_mappings:
    - url_pattern: "https://api.github.com/*"
      tool_name: "github::api"

    - url_pattern: "https://api.github.com/repos/*/issues"
      tool_name: "github::create-issue"
      methods: ["POST"]

    - url_pattern: "https://api.github.com/repos/*/issues/*"
      tool_name: "github::update-issue"
      methods: ["PATCH"]

    - url_pattern: "https://api.github.com/repos/*"
      tool_name: "github::delete-repo"
      methods: ["DELETE"]

    - url_pattern: "https://slack.com/api/chat.postMessage"
      tool_name: "slack::post-message"
      methods: ["POST"]

    - url_pattern: "https://*.amazonaws.com/*"
      tool_name: "aws::api"

# Enable policy enforcement
policy:
  enabled: true
  policy_file: ~/.bulwark/policies.yaml

# Enable credential vault
vault:
  enabled: true
  vault_dir: ~/.bulwark/vault

# Enable audit logging
audit:
  enabled: true
  database_path: ~/.bulwark/audit/audit.db

# Enable content inspection
content_inspection:
  enabled: true
  scan_requests: true
  scan_responses: true

Read the full file on GitHub · 763 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. yesterday First seen · 763 lines · 0 tokens per session scan A f56debf0f9c3

Subscribe to this mod's changes

codex is an agent published in the GitHub repository claudius-ars/bulwark (4 stars, last pushed 6mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,890 tokens. A static security scan graded it A with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens