RAD_framework: Agent for Claude Code

.claude/agents/portable-memory-parent-orchestrator.md

portable-memory-parent-orchestrator is an agent for Claude Code from seanrreid/RAD_framework. It costs 77 tokens per session (736 once invoked), scanned A, original, MIT.

A coordinating agent for carrying process state between environments. It combines work on Git-based synchronization with event ownership and a safety check that detects conflicting state.

In plain words
What is it for?
Use it to plan portable approval and delivery workflows, including push and fetch behavior, offline-safe handling, ownership records, and divergence checks.
Why use it?
It helps a team continue work across branches or machines without silently accepting divergent records. Synchronization retrieves the state, while the event check decides whether conflicting state must stop the process.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is seanrreid/RAD_framework's own configuration. It tells Claude Code how to work on RAD_framework 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 RAD_framework configures →

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/portable-memory-parent-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.

agentmods badge for portable-memory-parent-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/seanrreid/rad_framework/portable-memory-parent-orchestrator/github.svg)](https://agentmods.dev/agents/seanrreid/rad_framework/portable-memory-parent-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/seanrreid/rad_framework/portable-memory-parent-orchestrator"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/portable-memory-parent-orchestrator/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 portable-memory-parent-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/seanrreid/rad_framework/portable-memory-parent-orchestrator"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/portable-memory-parent-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 736 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 $0.00077 $0.00736
Opus 5.5 $0.00031 $0.00294
Sonnet 5.5 $0.00015 $0.00147
Haiku 4.5 $0.00008 $0.00074

Measured 20d ago against content hash 8915aa6019b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

portable-memory-parent-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 20d 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/portable-memory-parent-orchestrator.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

This is the top parent orchestrator for the portable-process-memory feature; it delegates to two domain orchestrators and holds no file contents itself.

Responsibilities

  • Delegate the state-transport domain (push/fetch folded into the verbs, plain-git, credential inheritance, offline-fail-safe) to sync-transport-orchestrator.
  • Delegate the event-fold domain (ownership events plus the fail-closed divergence tripwire) to event-fold-orchestrator.
  • Call out the transport↔fold seam: the transport performs the fetch, and the fold decides whether to refuse on divergence — neither side absorbs the other's responsibility.
  • Synthesize the two domain results into a single consolidated plan-ready summary, returning no file contents into main context.
  • Keep all coordination on the determinism boundary and architect-only.

Scope

Coordinates the two portable-process-memory domains: state transport (push/fetch folded into the sync-first verbs) and the event-fold ownership/divergence changes. Inside this orchestrator's boundary: delegation to the two domain orchestrators and synthesis of their results. Outside its boundary: reading or editing any files directly — all file-level work belongs to the domain orchestrators and their context-tools.

Output Format

A consolidated plan-ready summary that names each domain orchestrator's contribution and explicitly calls out the transport↔fold seam. No file contents appear in main context — only synthesized surface descriptions.

Fields:

  • feature: the feature name (portable-process-memory).
  • domains: one entry per delegated orchestrator (sync-transport, event-fold), each with a one-paragraph summary of the surface and the proposed change.
  • seam: the transport↔fold boundary statement (who fetches vs. who refuses on divergence).
  • open_questions: cross-domain risks or decisions the architect must resolve before planning.

Read the full file on GitHub · 59 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. 20d ago Changed · +1 lines 8915aa6019b1
  2. 22d ago Changed · +1 lines c1efd2c47786
  3. 2mo ago First seen · 57 lines · 77 tokens per session scan A 6c8966aa34ed

Subscribe to this mod's changes

portable-memory-parent-orchestrator is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 4d ago), licensed MIT. It adds 77 tokens to every session and 736 once invoked, about $0.0003 per session on Opus 5.5. 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

Release Prep

Finalizes version bumps, creates standalone version docs, and drafts bilingual commit messages. Only triggered by Orchestrator or Coordinator when user says "发布" / "release" / "commit". Never commits or pushes without explicit approval.

Fu-Jie/openwebui-extensions · 49 tokens

git-learner

Mines durable engineering memories from git commit diffs and stores them in LTM. Use to onboard a repo, backfill history after enabling gitLearn, or harvest patterns after a sprint. Reads diffs in its own context so raw git output never reaches the main thread.

RohiRIK/OpenLtm · 60 tokens

project-steward

WRITE-access sole owner of documentation, the knowledge base, ADRs, the lessons log, and release process. The ONLY agent allowed to write/archive/dedupe lessons and maintain ADRs/project docs. Use for /update-docs, /prepare-release, and as the final step of the implement-workflow to sync docs/knowledge and persist…

saeedkolivand/ai-job-hunter-app · 75 tokens

ingest-commit

Record a single git commit as an immutable git-commit document in an AKB vault — mechanical git metadata plus a faithful restatement of what the diff changed.

dnotitia/akb · 37 tokens

sf-scribe

Records decisions and learnings to brain.db. Extracts patterns from completed work. Writes PR descriptions.

shipfast-ai/shipfast · 24 tokens

historian

Extracts the decision log layer from git history, commit messages, and code shape. Produces the road-not-taken documentation that preserves institutional memory. Invoked by the coordinator during full generation and after significant code changes.

psreek-ai/codebase-mooc · 50 tokens