agentmods.dev

claude-orchestrator

A set of agent permission rules that allows 13 specific shell commands and reads files under the .orchestrator folder. It controls which actions the agent may perform in a project.

In plain words
What is it for?
Use it to configure an agent that can scan, execute, review, and finish tasks, inspect project status and history, and commit or push changes.
Why use it?
It limits the agent to a defined list of commands, making its actions easier to review and control. The rules include common Git actions and project scripts.

Settings file for Claude Code

2 2mo ago A scan tokens not measured original MIT
View the source file Tainmat/claude-orchestrator
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 settings/tainmat/claude-orchestrator/settings
Clone the repo
git clone --depth 1 https://github.com/Tainmat/claude-orchestrator

Made for: Claude Code.

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 A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

claude-orchestrator scanned grade A 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.

Makes network callslowCapability

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

"Bash(curl -s -X POST:*)",
template/.claude/settings.json · 21 lines

What it actually says

{
  "permissions": {
    "allow": [
      "Bash(bash .claude/scripts/scan.sh:*)",
      "Bash(bash .claude/scripts/execute.sh:*)",
      "Bash(bash .claude/scripts/review.sh:*)",
      "Bash(bash .claude/scripts/finish-task.sh:*)",
      "Bash(git diff:*)",
      "Bash(git status:*)",
      "Bash(git log:*)",
      "Bash(git add:*)",
      "Bash(git commit:*)",
      "Bash(git push:*)",
      "Bash(curl -s -X POST:*)",
      "Bash(cat .orchestrator/:*)",
      "Read(.orchestrator/**)"
    ],
    "deny": []
  }
}
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 · 21 lines scan A f0e5c972cecc

Subscribe to this mod's changes

claude-orchestrator is a settings file published in the GitHub repository Tainmat/claude-orchestrator (2 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 A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other settings, from other repositories

supabase

Agent settings declaring 2 hook events (SessionStart, PostToolUse).

supabase/supabase · not measured

superset

Agent settings declaring 1 hook event (PreToolUse).

apache/superset · not measured

claude-cookbooks

Agent settings declaring 2 hook events (SessionStart, PreToolUse).

anthropics/claude-cookbooks · not measured

claude-code-best-practice

Agent settings declaring 30 hook events (PreToolUse, PermissionRequest, PostToolUse, PostToolUseFailure) and 24 allowed tools.

shanraisshan/claude-code-best-practice · not measured

electron

Agent settings declaring 17 allowed tools.

electron/electron · not measured

uv

Agent settings declaring 2 hook events (SessionStart, PostToolUse).

astral-sh/uv · not measured