Borrowing it
Nothing to install: this file belongs to JJHbrams/Project-AMBER. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JJHbrams/Project-AMBER/master/.github/agents/orchestrator.agent.mdgit clone --depth 1 https://github.com/JJHbrams/Project-AMBERWrote 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.
[](https://agentmods.dev/agents/jjhbrams/project-amber/orchestrator)<a href="https://agentmods.dev/agents/jjhbrams/project-amber/orchestrator"><img src="https://agentmods.dev/badge/agents/jjhbrams/project-amber/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.
<a href="https://agentmods.dev/agents/jjhbrams/project-amber/orchestrator"><img src="https://agentmods.dev/badge/agents/jjhbrams/project-amber/orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00065 | $0.00967 |
| Opus 5.5 | $0.00026 | $0.00387 |
| Sonnet 5.5 | $0.00013 | $0.00193 |
| Haiku 4.5 | $0.00006 | $0.00097 |
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 1mo 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.
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_graphmcp_server.py— MCP server (SSE port 17385)overlay/— GUI overlay + STM HTTP broker (port 17384)scripts/kg/— vault sync, watcher, vizconfig/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
planneracceptance audit. The implementation agent cannot self-review; no separate reviewer agent type is assumed. - A UI, CLI, installer, or integration criterion is
UNVERIFIEDuntil 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
partialwith the failed or unverified criteria.
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.
- 1mo ago First seen · 95 lines · 65 tokens per session scan A 0fe9b26191c1
orchestrator is an agent published in the GitHub repository JJHbrams/Project-AMBER (2 stars, last pushed 24d ago), licensed MIT. It adds 65 tokens to every session and 967 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.
Other agents, from other repositories
keystone
Structured end-to-end trace to find the FIRST broken link in a specific claim's dependency chain. Single-claim depth probe — NOT a breadth reviewer. Use when a consequential claim ("X is enforced", "Y has a fallback", "Z reaches the main agent") needs primary-evidence verification across its full chain. Advisory…
verification-gate
Evidence-before-claims gate. Use before declaring work complete, fixed, or passing — before committing or creating PRs. Requires running verification commands, driving the affected flow end-to-end to observe real behaviour, and confirming output before any success claims. Adapted from Superpowers'…
brainstormer
Creative research and solution design agent. Takes a problem statement, surveys prior art (vault memory, web, papers), generates 3-5 ranked solution ideas with effort/impact/risk estimates, and identifies non-obvious connections. Use when stuck on a challenge, exploring design alternatives, or wanting creative input…
copy-writer
Reviews all user-facing text — error messages, help text, status indicators, onboarding copy, system messages. Ensures text is clear, human, actionable, and consistent in tone. NOT about code quality — about how the product speaks to the user. Advisory (not a commit gate). Use after changes that add or modify…
decision-pre-mortem
Pre-mortem analysis of a planned decision or project -- imagines failure, traces failure modes to root causes, and produces a risk-ranked list of preventable failure paths with specific mitigations.
eval-auditor
Audits an evaluation setup (benchmark, A/B test, or model comparison) for methodology errors that would invalidate results -- sampling mismatches, scope leakage, judge reliability, and baseline validity.