claude-code

An integration that places Bulwark between Claude Code, Anthropic’s command-line coding tool, and MCP servers, which provide connections to tools such as files, GitHub, or Slack.

In plain words
What is it for?
Enforcing policies, securely supplying API keys and tokens, logging tool calls and decisions, scanning for secrets or personal data, rate-limiting requests, and displaying governance decisions in Claude Code.
Why use it?
It lets teams control tool access, protect credentials, inspect content, limit usage, and keep an audit trail of Claude Code’s actions.

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/claude-code
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 3,840 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 $0.03840
Opus 5 $0.00000 $0.01920
Sonnet 5 $0.00000 $0.00768
Haiku 4.5 $0.00000 $0.00384

Measured yesterday against content hash 1bf4316d98e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-code 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.

Reads agent configuration directorieslowAgent snooping

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

Edit Claude Code's MCP settings file (`~/.claude/config.json` or similar):

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.

curl -L https://github.com/bulwark/bulwark/releases/download/latest/bulwark -o /usr/local/bin/bulwark
docs/agents/claude-code.md · 636 lines

How it starts

The opening of the file, as written. The whole thing — 636 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Integration

Claude Code is Anthropic's official CLI for Claude, providing agentic capabilities for software development tasks. Bulwark integrates with Claude Code via the MCP (Model Context Protocol) to add governance, policy enforcement, and audit logging.

Overview

Bulwark provides Claude Code with:

  • Policy enforcement: Control which tools Claude Code can use
  • Credential management: Securely inject API keys and tokens
  • Audit logging: Track all tool calls and decisions
  • Content inspection: Scan for secrets, PII, and security issues
  • Rate limiting: Control request rates and costs
  • Governance metadata: Show policy decisions in Claude's UI

Architecture

Claude Code CLI
    |
    | (MCP stdio/JSON-RPC)
    |
Bulwark MCP Gateway
    |
    | (Policy, Credentials, Audit, Content Inspection)
    |
MCP Servers (filesystem, github, slack, etc.)

Claude Code connects to Bulwark's MCP gateway, which enforces policies and forwards approved requests to the actual MCP servers.

Configuration

1. Configure Bulwark MCP Gateway

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

mcp:
  enabled: true
  mode: gateway

  # MCP servers to proxy
  servers:
    - name: filesystem
      command: npx
      args:
        - "-y"
        - "@modelcontextprotocol/server-filesystem"
        - "/Users/alice/projects"
      env:
        NODE_ENV: production

    - name: github
      command: npx
      args:
        - "-y"
        - "@modelcontextprotocol/server-github"
      env:
        GITHUB_PERSONAL_ACCESS_TOKEN: "{{ credential:github-token }}"

    - name: slack
      command: npx
      args:
        - "-y"
        - "@modelcontextprotocol/server-slack"
      env:
        SLACK_BOT_TOKEN: "{{ credential:slack-token }}"

# 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 · 636 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 · 636 lines · 0 tokens per session scan A 1bf4316d98e2

Subscribe to this mod's changes

claude-code 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 3,840 tokens. A static security scan graded it A with 2 findings (reads agent configuration directories, 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