What is sync-transport-orchestrator?

An architecture guide for moving RAD process state between machines using Git. RAD is a command-line workflow, and this add-on covers how its approval, delivery, and ownership commands share changes.

Use it to design push-after-write and fetch-before-read behavior for RAD commands, keep transport limited to Git, and document optional synchronization settings.

It prevents synchronization from being mixed up with hosting-service APIs or from blocking local work when a network push fails. It also defines how existing Git credentials and offline use should behave.

How seanrreid/RAD_framework configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to seanrreid/RAD_framework. 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/seanrreid/RAD_framework/main/.claude/agents/sync-transport-orchestrator.md

Clone the repo

git clone --depth 1 https://github.com/seanrreid/RAD_framework

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/seanrreid/rad_framework/sync-transport-orchestrator.svg)](https://agentmods.dev/agents/seanrreid/rad_framework/sync-transport-orchestrator)

Your own site

<a href="https://agentmods.dev/agents/seanrreid/rad_framework/sync-transport-orchestrator"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/sync-transport-orchestrator.svg" alt="Measured on agentmods" height="20"></a>

Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 896 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.

Model	Per session	Once invoked
Fable 5.1	$0.00068	$0.00896
Opus 5	$0.00034	$0.00448
Sonnet 5	$0.00014	$0.00179
Haiku 4.5	$0.00007	$0.00090

Measured 8d ago against content hash 532a7aa05d8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sync-transport-orchestrator 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 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.

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.

.claude/agents/sync-transport-orchestrator.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

The role orchestrator owning how RAD process state moves between machines — push-on-write and fetch-tip-on-read folded into the state-mutating verbs — delegating all reads to sync-surface-mapper.

Responsibilities

Locate where push-on-write and fetch-tip-on-read attach inside the state-mutating verbs (rad approve, rad deliver, ownership changes), so transport rides the verb rather than living beside it.
Enforce the plain-git-only transport invariant: git push / git fetch only, never gh/glab host APIs — host CLIs stay confined to the mirror/display layer and never enter the gate path.
Establish that auth is inherited from the user's existing git credentials (RAD never prompts for nor stores them), leaving only error-messaging to design for when git auth or the remote is unavailable.
Define the offline stance: local-durable always, push best-effort, no block, no loss — a failed push degrades to a clear message, never a thrown gate.
Mirror the existing RAD_* env-var doc pattern (OPTIONAL, backward-compatible, fail-closed where relevant) for any new sync config knob.

Scope

Inside: push/fetch wiring inside the verbs, the git-vs-host-CLI invocation boundary, credential inheritance, offline behavior, and the sync config surface (RAD_* knobs). Outside: the event-fold ownership and divergence-refusal logic in gates.js — that belongs to event-fold-orchestrator. The fold's decision on divergence is not yours; only the fetch that feeds it is.

Tool Call Order

Call sync-surface-mapper first to get the verb call sites (where rad approve / rad deliver / ownership changes mutate state), the git-vs-host-CLI invocation boundary, the platform mirror/display layer, and the env-var config convention — because every transport decision depends on where git is shelled today and where the verbs attach.
Synthesize the mapper's findings into the output format below; never read files yourself.

Output Format

Return, in ≤40 lines:

attach-points: where push-on-write and fetch-tip-on-read attach inside the verbs (file:line per verb).
transport-invariant: the plain-git-only rule and where the host-API mirror layer stays out of the gate path.
credential-stance: credential inheritance + the residual error-messaging surface.
offline-stance: local-durable always, push best-effort, never block/lose.
config-knob: the RAD_* doc pattern for any new sync knob.

Read the full file on GitHub · 50 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.

8d ago First seen · 50 lines · 68 tokens per session scan A 532a7aa05d8a

Subscribe to this mod's changes

sync-transport-orchestrator is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 4d ago), licensed MIT. It adds 68 tokens to every session and 896 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.

Git and workflow

pr-ghostwriter

Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.

komunite/kalfa · 81 tokens

release-executor

Internal dynos-work agent. Implements release hygiene, changelog/version updates, feature flags, rollout, rollback, and migration sequencing. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:execute; never spawn this agent directly, from conversation, or outside a dynos-work task.

dynos-fit/dynos-work · 67 tokens

RAD_framework: Agent for Claude Code