ai901-cert-buddy-claude: Settings file for Claude Code

.claude/settings.json

ai901-cert-buddy-claude is a settings file for Claude Code from timothywarner-org/ai901-cert-buddy-claude. Its token cost is not measured, scanned C, original, MIT.

Agent settings for an AI-901 certification study assistant, with a study-coach response style, selected reading and research tools, and four automated checks during a session.

In plain words
What is it for?
They are for reading study material, adding context to prompts, and using the configured AI-901 and certification-coach services during exam preparation.
Why use it?
They keep the assistant focused on certification study and restrict it from using broader editing or shell capabilities, while blocking destructive commands.

Settings file for Claude Code

Written for Claude Code: $CLAUDE_PROJECT_DIR variable.

This is timothywarner-org/ai901-cert-buddy-claude's own configuration. It tells Claude Code how to work on ai901-cert-buddy-claude itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai901-cert-buddy-claude configures →

One of 5 entries in settings.json upstream. Installing this one merges just its entry into your config; the other 4 are separate, each on its own page.

Reuse

Borrowing it

Nothing to install: this file belongs to timothywarner-org/ai901-cert-buddy-claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/timothywarner-org/ai901-cert-buddy-claude/main/.claude/settings.json
Clone the repo
git clone --depth 1 https://github.com/timothywarner-org/ai901-cert-buddy-claude

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ai901-cert-buddy-claude

README.md
[![agentmods](https://agentmods.dev/badge/settings/timothywarner-org/ai901-cert-buddy-claude/settings.svg)](https://agentmods.dev/settings/timothywarner-org/ai901-cert-buddy-claude/settings)
Your own site
<a href="https://agentmods.dev/settings/timothywarner-org/ai901-cert-buddy-claude/settings"><img src="https://agentmods.dev/badge/settings/timothywarner-org/ai901-cert-buddy-claude/settings.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade C, and why

ai901-cert-buddy-claude scanned grade C 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 8d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

"Bash(rm -rf:*)",
.claude/settings.json · 64 lines

What it actually says

{
  "$schema": "https://json.schemastore.org/claude-code-settings.json",
  "_comment": "Project settings for AI-901 Cert Buddy. Four hook events make the buddy's promises deterministic; the project MCP servers are enabled by default; the Cert Coach output style sets the study-coach voice; least-privilege permissions keep the agent on rails. Hook commands use 'python' for Windows-first turnkey; on macOS or Linux you may need 'python3'.",
  "enableAllProjectMcpServers": true,
  "outputStyle": "Cert Coach",
  "permissions": {
    "allow": [
      "Read",
      "Grep",
      "Glob",
      "mcp__ai901buddy-mslearn",
      "mcp__cert-buddy"
    ],
    "deny": [
      "Bash(rm -rf:*)",
      "Bash(git clean:*)"
    ]
  },
  "hooks": {
    "SessionStart": [
      {
        "hooks": [
          {
            "type": "command",
            "command": "python \"$CLAUDE_PROJECT_DIR/.claude/hooks/session-start.py\""
          }
        ]
      }
    ],
    "UserPromptSubmit": [
      {
        "hooks": [
          {
            "type": "command",
            "command": "python \"$CLAUDE_PROJECT_DIR/.claude/hooks/prompt-context.py\""
          }
        ]
      }
    ],
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "python \"$CLAUDE_PROJECT_DIR/.claude/hooks/policy-gate.py\""
          }
        ]
      }
    ],
    "PostToolUse": [
      {
        "matcher": "mcp__ai901buddy-mslearn__.*",
        "hooks": [
          {
            "type": "command",
            "command": "python \"$CLAUDE_PROJECT_DIR/.claude/hooks/citation-audit.py\""
          }
        ]
      }
    ]
  }
}
Same file

What else settings.json configures

This page is one entry in a file that holds 5. Installing the file brings all of them; each is measured and scanned on its own page.

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. 8d ago First seen · 64 lines scan C 25a086786246

Subscribe to this mod's changes

ai901-cert-buddy-claude is a settings file published in the GitHub repository timothywarner-org/ai901-cert-buddy-claude (9 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.