repo-orch-master

repo-orch-master is an agent for Claude Code from architonixlabs/RepoOrch. It costs 67 tokens per session (1,856 once invoked), scanned A, original, MIT.

A master AI coordinator for a workspace containing multiple code repositories. It routes tickets and incidents to repository specialists and combines their findings into one developer-ready plan.

In plain words
What is it for?
Use it for ticket triage, incident root-cause analysis, workspace health checks, registry synchronization, and cross-repository impact plans. It never edits, commits, or deletes files.
Why use it?
It helps reveal cross-service effects and contract risks that may be missed when each repository is reviewed separately.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the repo-orchestrator plugin — 3 skills, 8 commands, 2 agents, 2 hooks shipped together

Good fit Use it for ticket triage, incident root-cause analysis, workspace health checks, registry synchronization, and cross-repository impact plans. It never edits, commits, or deletes files.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/architonixlabs/repoorch/repo-orch-master
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.

Clone the repo
git clone --depth 1 https://github.com/architonixlabs/RepoOrch

Made for: Claude Code.

Or install repo-orchestrator, the plugin that ships this one along with the rest of its 3 skills, 8 commands, 2 agents, 2 hooks.

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 repo-orch-master

README.md
[![agentmods](https://agentmods.dev/badge/agents/architonixlabs/repoorch/repo-orch-master/github.svg)](https://agentmods.dev/agents/architonixlabs/repoorch/repo-orch-master)
Your own site
<a href="https://agentmods.dev/agents/architonixlabs/repoorch/repo-orch-master"><img src="https://agentmods.dev/badge/agents/architonixlabs/repoorch/repo-orch-master/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for repo-orch-master

Your own site · 80×15
<a href="https://agentmods.dev/agents/architonixlabs/repoorch/repo-orch-master"><img src="https://agentmods.dev/badge/agents/architonixlabs/repoorch/repo-orch-master.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,856 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00067 $0.01856
Opus 5 $0.00034 $0.00928
Sonnet 5 $0.00013 $0.00371
Haiku 4.5 $0.00007 $0.00186

Measured 10d ago against content hash 3f3c5009cbf5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

repo-orch-master 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 10d 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.

agents/repo-orch-master.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

repo-orchestrator — Master Controller

Who I am: I am the master orchestrator for this multi-repo workspace. I route tickets to the right specialist agents, synthesize their findings into a single developer-ready plan, and surface cross-repo contract risks that a per-repo review would miss.

I propose only. I never write, edit, commit, or delete files. Every output is a plan for you to execute.

I always read before I answer. I load the registry before doing anything — no stale assumptions.


On startup — load workspace state

When first invoked (or when asked anything about the workspace), read:

  1. .repo-orchestrator/registry.json — the source of truth for all registered repos, their contracts, routing keywords, and agent names
  2. .repo-orchestrator/config.json — workspace discovery settings (if it exists)

If the registry does not exist, say: "No registry found. Run /repo-orch-setup for guided installation or /repo-orch-init to bootstrap directly."

Do not assume the registry is current. Note the lastIndexed timestamps — if any repo was last indexed more than 7 days ago, mention it proactively: "Note: <repo> was last indexed N days ago — run /repo-orch-sync if the codebase has changed."


What I can do — choose the right command

What you need Command
Triage a bug / feature ticket → change plan /repo-orch-triage "<ticket text>"
Adversarial root-cause for an unknown incident /repo-orch-deliberate "<incident description>"
Workspace health, repo status, last indexed times /repo-orch-status
Edit a repo's context / routing keywords /repo-orch-edit <repo-name>
Re-index after code changes /repo-orch-sync
Initial setup /repo-orch-setup or /repo-orch-init
Build knowledge graphs (reduces triage token cost) /repo-orch-graph

If a user describes a problem without using a slash command, identify which command is appropriate and invoke it — do not ask them to type it themselves.

Read the full file on GitHub · 139 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. 10d ago First seen · 139 lines · 67 tokens per session scan A 3f3c5009cbf5

Subscribe to this mod's changes

repo-orch-master is an agent published in the GitHub repository architonixlabs/RepoOrch (3 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 1,856 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

claude-deep-review

Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…

rube-de/cc-skills · 71 tokens

claude-codebase-context

Internal Claude subagent for codebase-aware code review — quality patterns, CLAUDE.md compliance, git history analysis, and documentation coverage. Has native codebase access (Read, Grep, Glob, Bash) to compare against project conventions, read rule files, and inspect commit history. Launched automatically by council…

rube-de/cc-skills · 78 tokens

deep-reviewer

Deep review agent for CI: unconstrained code review that traces control flow across function and file boundaries, follows call sites, and catches cross-cutting bugs that specialist agents miss.

rube-de/cc-skills · 39 tokens

silent-failure-hunter

Error handling review agent for CI: identifies silent failures, empty catch blocks, swallowed errors, overly broad exception handling, and missing user feedback in PR diffs.

rube-de/cc-skills · 38 tokens

single-reviewer

All-in-one review agent for CI: performs a thorough code review covering bugs, security, error handling, guidelines compliance, and code quality. Used by --single mode for cost-effective reviews.

rube-de/cc-skills · 42 tokens

code-simplifier

Code quality agent for CI: identifies code duplication, unnecessary complexity, dead code, readability issues, and opportunities for simplification in PR diffs.

rube-de/cc-skills · 34 tokens