agentmods.dev

repo-orch-sync

repo-orch-sync is a command for Claude Code from architonixlabs/RepoOrch. It costs 34 tokens per session (1,553 once invoked), scanned A, original, MIT.

A command that refreshes a registry of repositories and re-indexes repositories that have changed. A repository is a project folder containing code and its version history.

In plain words
What is it for?
Use it to refresh every registered repository or one named repository, detect stale entries, and bring stored repository context back into the registry.
Why use it?
It keeps repository information current as folders and files change, while preserving content that a user edited. It can also identify registry entries whose folders no longer exist.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

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

not rated 3repo 2mo ago A scan 34 tokens original MIT

Good fit Use it to refresh every registered repository or one named repository, detect stale entries, and bring stored repository context back into the registry.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/architonixlabs/repoorch/repo-orch-sync
View source ↗ architonixlabs/RepoOrch
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-sync

README.md
[![agentmods](https://agentmods.dev/badge/commands/architonixlabs/repoorch/repo-orch-sync/github.svg)](https://agentmods.dev/commands/architonixlabs/repoorch/repo-orch-sync)
Your own site
<a href="https://agentmods.dev/commands/architonixlabs/repoorch/repo-orch-sync"><img src="https://agentmods.dev/badge/commands/architonixlabs/repoorch/repo-orch-sync/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-sync

Your own site · 80×15
<a href="https://agentmods.dev/commands/architonixlabs/repoorch/repo-orch-sync"><img src="https://agentmods.dev/badge/commands/architonixlabs/repoorch/repo-orch-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,553 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 $0.00034 $0.01553
Opus 5 $0.00017 $0.00776
Sonnet 5 $0.00007 $0.00311
Haiku 4.5 $0.00003 $0.00155

Measured 10d ago against content hash be632a6b7fc4, 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-sync 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.

commands/repo-orch-sync.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/repo-orch-sync [repo]

Refresh the registry for all repos, or a single named repo.

Usage:

  • /repo-orch-sync — refresh all repos
  • /repo-orch-sync auth-service — refresh only the auth-service repo

Step 1 — Load registry

Read .repo-orchestrator/registry.json. If it does not exist, stop: "Registry not found. Run /repo-orch-init first."

If a repo name was provided, find that entry. If not found, stop: "Repo <name> not found in registry. Available: list all names from the registry."

Step 1.5 — Detect stale entries (full sync only)

Skip this step when a specific repo name was provided.

For each entry in the registry, check whether its path still exists on disk as a directory. If it does not:

  1. Flag it as stale and print:

    ⚠️  Stale registry entry: '<name>' — path '<path>' no longer exists.
   This repo may have been deleted or renamed.
   Remove it? [y/N]

  2. If the user says Y:

    • Delete .claude/agents/repo-<name>.md if it exists.
    • Delete .repo-orchestrator/context/<name>.md if it exists.
    • Delete .repo-orchestrator/skills/<name>.md if it exists.
    • Delete .repo-orchestrator/graphs/<name>/ directory if it exists.
    • Remove the entry from the registry object (do not write yet — the write happens in Step 5).

  3. If the user says N: leave the entry in place and continue. It will remain stale until removed manually or re-confirmed at the next sync.

After processing all stale entries, continue with Step 2 for the remaining (non-stale) entries only.

Step 2 — Detect drift

For each repo to process:

  1. Compute a fresh fingerprint using the method from skills/repo-indexing/SKILL.md.
  2. Compare to the registry.json entry's fingerprint.
  3. Check if the context file (.repo-orchestrator/context/<name>.md) was modified after lastIndexed (compare file mtime to the lastIndexed timestamp).

Decision:

  • If fingerprint unchanged AND context file not modified: repo is up to date — skip and report "No drift detected."
  • If fingerprint changed AND context file is NOT newer than lastIndexed: code has changed — re-index (Step 3a only).
  • If context file is newer than lastIndexed AND fingerprint is unchanged: user made manual edits — ingest frontmatter (Step 3b only).
  • If both fingerprint changed AND context file is newer than lastIndexed: run Step 3a to re-index, then immediately run Step 3b to merge the user's manual edits on top of the re-indexed values. Set userEdited: true in the registry entry regardless of the outcome — the user has made intentional edits that must survive future syncs.

Read the full file on GitHub · 136 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 · 136 lines · 34 tokens per session scan A be632a6b7fc4

Subscribe to this mod's changes

repo-orch-sync is a command published in the GitHub repository architonixlabs/RepoOrch (3 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 1,553 once invoked, about $0.0002 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.

Claude CodeGit and workflowagent-teamsai-agentsclaude-code-plugindevtoolsmicroservices
Related

Other commands, from other repositories

proof-report

Generate a Launch Proof Report for an existing repo by combining release, publish, and security audit evidence.

starter-series/create-starter · 20 tokens

audit-release

Diagnose release-readiness against the Starter Series quality bar — matched starter, version-vs-last-tag drift, CHANGELOG drift vs merged PRs, and publish-workflow kind. Read-only.

starter-series/create-starter · 39 tokens

context

A project-context command that manages a .context directory containing decision notes, session logs, and history. It helps keep a record of why changes were made across Git branches and commits.

fengshao1227/ccg-workflow · 23 tokens

git

The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.

azrtydxb/procoder · 20 tokens

composite-actions

Generate, review, secure, and test composite GitHub Actions following best practices — full repo scaffold, interview-driven generation, PR creation on existing repos, SHA pinning, secrets-as-inputs, job summaries, and actionlint validation.

nitinjain999/platform-skills · 51 tokens

release

Generate changelog, bump version, and create git tag.

Joncik91/ucai · 11 tokens