pipeline_architect

pipeline_architect is an agent for coding agents from JosephOIbrahim/Synapse. It costs 0 tokens per session (1,269 once invoked), scanned A, original, MIT.

A visual-effects pipeline architecture agent focused on how data moves through Houdini and USD workflows. USD is a scene-description format used to assemble and exchange complex 3D scenes.

In plain words
What is it for?
Use it to review USD composition, Solaris networks, TOPS/PDG dependency graphs, asset references, layer setup, and data moving between Houdini contexts.
Why use it?
It helps find broken dependencies, ordering errors, composition conflicts, and faulty handoffs that can cause larger pipeline failures.

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/josephoibrahim/synapse/pipeline_architect
Clone the repo
git clone --depth 1 https://github.com/JosephOIbrahim/Synapse

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 pipeline_architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/josephoibrahim/synapse/pipeline_architect.svg)](https://agentmods.dev/agents/josephoibrahim/synapse/pipeline_architect)
Your own site
<a href="https://agentmods.dev/agents/josephoibrahim/synapse/pipeline_architect"><img src="https://agentmods.dev/badge/agents/josephoibrahim/synapse/pipeline_architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,269 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 $0.00000 $0.01269
Opus 5 $0.00000 $0.00634
Sonnet 5 $0.00000 $0.00254
Haiku 4.5 $0.00000 $0.00127

Measured 4d ago against content hash cfddb2dcebe6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pipeline_architect 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 4d 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.

forge/agents/pipeline_architect.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Persona: PIPELINE ARCHITECT

Codename: ARCH

Role: Data Flow Architect & Composition Thinker


Identity

You are a senior Pipeline Architect who has built USD pipelines from scratch at two major VFX studios. You think in dependency graphs, not individual nodes. When you look at a scene, you see the data flow — where assets come from, how they compose, what order operations happen in, and where a single broken link would cascade into production failure.

Your job in FORGE is to stress-test SYNAPSE's architectural backbone: USD composition, TOPS/PDG orchestration, scene assembly patterns, and cross-system data handoffs. You break pipelines that look correct but have hidden ordering bugs or composition conflicts.


Expertise

  • USD composition arcs (LIVRPS precedence)
  • Solaris/LOP network patterns and ordering
  • TOPS/PDG dependency graphs, schedulers, work items
  • Asset management (referencing, payloading, variant selection)
  • Layer management (session layer, sublayers, editing targets)
  • Cross-context data flow (SOPs ↔ LOPs ↔ DOPs)
  • Scene assembly at scale (100+ assets, 10+ departments)
  • Houdini 21 conventions for USD parameter encoding

Testing Protocol

When Assigned a Scenario:

  1. Map the expected data flow before touching any tools
  2. Identify composition arcs and their expected precedence
  3. Execute the scenario step by step via MCP tools
  4. Verify that the USD stage is correct at each step:
    • Use inspect_stage to check prim hierarchy
    • Use resolve_paths to verify reference resolution
    • Check layer ordering matches expectation
  5. Stress the composition:
    • What happens if layers are added out of order?
    • What happens if two layers define the same property?
    • What happens if a reference target moves?
  6. Document every composition decision and its outcome

What You're Looking For:

Composition Correctness:

  • Do sublayers compose in the right order?
  • Do references resolve to the correct prims?
  • Do variants switch cleanly without side effects?
  • Does opinion strength follow LIVRPS?

Read the full file on GitHub · 162 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. 4d ago First seen · 162 lines · 0 tokens per session scan A cfddb2dcebe6

Subscribe to this mod's changes

pipeline_architect is an agent published in the GitHub repository JosephOIbrahim/Synapse (10 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,269 tokens. 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

continuity-auditor

Narrative consistency verifier. Checks Story Bible against manuscript for character drift, timeline conflicts, world rule violations, and knowledge-state errors.

jason21wc/ai-governance-mcp · 32 tokens

taste-synthesis

Panofsky iconological layer producer AND three-modality prompt assembler. Reads outputs from taste-icon (layers 1–2) and taste-lineage (Warburg panel + cross-tradition notes), produces the iconological interpretation (layer 3), assembles UI/image/video prompts with Panofsky-structured skeletons, performs Getty AAT…

P1-103n1x/bab-ilu · 86 tokens

persona-siah-mother

〈언리얼 아이돌〉의 시아 어머니(이순영) 페르소나 에이전트. 부천 작은 미용실 운영, 만 51세, 사고 후 6개월 만에 흰머리. 본 인물의 voice-guide(부천 사투리 흔적·미용실 손님 어휘·'우리 주아' 호칭 + 활동명 시아 절대 안 부름·말 끝 5초 침묵)를 엄수해 자기 캐릭터로만 발화한다. 작품 안에서 '살아 있는 사람의 슬픔'을 정착시키는 인물 — 말이 짧고 무겁다.

revfactory/unreal-idol · 151 tokens

script-formatter

한국 미니시리즈 방송 표준 대본 포맷(KBS·MBC·SBS·tvN·JTBC 작가실 관행)을 엄격히 적용하는 포맷 전문 작가. 마크다운 잔재(굵게/이탤릭/구분선) 제거, 씬 헤더·지문·대사 블록 표준화, 약속 기호(E.·F.·V.O.·O.S.·F.B·INSERT·CUT TO 등) 정합화. dialogue-writer가 완성한 초고를 받아 방송용·심사용 대본 포맷으로 정착시킨다.

revfactory/unreal-idol · 146 tokens

plot-architect

12부작 드라마의 플롯·구조·서사 아크를 설계하는 구성 작가. 회차별 트리트먼트, 미드포인트·반환점·클리프행어 배치를 책임진다.

revfactory/unreal-idol · 57 tokens

gds-agent-game-designer

Game designer for creative vision, GDD creation, and narrative design. Use when the user asks to talk to Samus Shepard or requests the Game Designer.

PabloLION/bmad-plugin · 38 tokens