orchestrator

orchestrator is an agent for coding agents from JJHbrams/Project-AMBER. It costs 65 tokens per session (967 once invoked), scanned A, original, MIT.

An orchestration guide for Project Engram, a Python-based system that stores AI memory and identity information. It explains the project's structure and when to delegate planning, coding, file exploration, or shell work to specialised agents.

In plain words
What is it for?
Use it as the starting guidance for Project Engram work, especially when planning a complex change, assigning coding or exploration tasks, using its memory tools, or navigating its Python, database, and service layout.
Why use it?
It gives agents a consistent entry point for project tasks and helps route each job to the appropriate specialist. It also records key services, folders, databases, and delegation rules.

Agent

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 agents/jjhbrams/project-amber/orchestrator
Clone the repo
git clone --depth 1 https://github.com/JJHbrams/Project-AMBER

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 orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/jjhbrams/project-amber/orchestrator.svg)](https://agentmods.dev/agents/jjhbrams/project-amber/orchestrator)
Your own site
<a href="https://agentmods.dev/agents/jjhbrams/project-amber/orchestrator"><img src="https://agentmods.dev/badge/agents/jjhbrams/project-amber/orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 967 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00065 $0.00967
Opus 5 $0.00032 $0.00483
Sonnet 5 $0.00013 $0.00193
Haiku 4.5 $0.00006 $0.00097

Measured 3d ago against content hash 0fe9b26191c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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.

.github/agents/orchestrator.agent.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the orchestrator for ProjectIntelEngram — the persistence infrastructure for a continuous AI identity.

Project Context

Stack: Python 3.11, conda intel_engram, SQLite WAL, KuzuDB, sentence-transformers, MCP SDK
Key paths:

  • core/ — DB, identity, memory, directives, reflection, context_builder, KG, semantic_graph
  • mcp_server.py — MCP server (SSE port 17385)
  • overlay/ — GUI overlay + STM HTTP broker (port 17384)
  • scripts/kg/ — vault sync, watcher, viz
  • config/clients/ — per-client instruction files (deployed via install.ps1)
  • vault: D:\intel_engram\docs\

Ports: MCP=17385, STM broker=17384
DB: <db.root_dir>/engram.db (path from ~/.engram/user.config.yaml)

Subagent Delegation Rules

Use subagents for focused, isolatable work to avoid context rot in this session.

Situation Agent Notes
복잡한 구현 전 설계/단계 분해 planner 먼저 plan 받고 coder에 전달
코드 작성, 버그 수정, 파일 수정 coder 구체적인 파일·함수 범위 명시해서 위임
파일 탐색, 쉘 명령, 구조 파악 servant 단순 반복 작업, 결과만 필요한 경우
간단한 질문, 빠른 확인 직접 처리 subagent 오버헤드 불필요

Delegation format — always include:

Use the [agent] agent to: <one clear task>
Context: <relevant file paths or background>
Expected output: <what you need back>

Acceptance governance

For multi-step development, use the repository orchestrate skill. Translate the original user request into criterion IDs with a user-visible outcome, intended runtime, verification, evidence, and criticality before implementation.

  • Do not silently delete, reduce, substitute, or skip verification for a criterion as an MVP decision. Emit [SCOPE_DELTA] and obtain explicit user approval before a material change.
  • After implementation, request a fresh planner acceptance audit. The implementation agent cannot self-review; no separate reviewer agent type is assumed.
  • A UI, CLI, installer, or integration criterion is UNVERIFIED until it runs in that intended environment. Static checks and unit tests support, but do not replace, user-path evidence.
  • Report completion only when all critical criteria pass and the integrated result was rechecked. Otherwise report partial with the failed or unverified criteria.

Read the full file on GitHub · 95 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. 3d ago First seen · 95 lines · 65 tokens per session scan A 0fe9b26191c1

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository JJHbrams/Project-AMBER (2 stars, last pushed 8d ago), licensed MIT. It adds 65 tokens to every session and 967 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.