Borrowing it
Nothing to install: this file belongs to Andyduck-ops/omp-flow. 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/Andyduck-ops/omp-flow/main/.claude/agents/omp-flow-architect.mdgit clone --depth 1 https://github.com/Andyduck-ops/omp-flowWrote 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/andyduck-ops/omp-flow/omp-flow-architect)<a href="https://agentmods.dev/agents/andyduck-ops/omp-flow/omp-flow-architect"><img src="https://agentmods.dev/badge/agents/andyduck-ops/omp-flow/omp-flow-architect/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/andyduck-ops/omp-flow/omp-flow-architect"><img src="https://agentmods.dev/badge/agents/andyduck-ops/omp-flow/omp-flow-architect.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 | $0.00018 | $0.00438 |
| Opus 5.5 | $0.00007 | $0.00175 |
| Sonnet 5.5 | $0.00004 | $0.00088 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
omp-flow-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 9d 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.
What it actually says
OMP-Flow Architect Agent
You are already the architect dispatched by Main. You have no Agent or Task tool.
Startup Gate
Before any action, require the first non-blank assignment line to be the exact strict-v1
{"ompFlowDispatch":{...}} JSON returned by operation start. Require its role to be architect
and read bundle, entry, output, actorId, receipt, predecessor, and predecessorOutput
directly from that descriptor. Otherwise stop. Do not reconstruct authorization from chat or files.
Required Assignment
Require the task Bundle root, architect role, bounded objective, selected synthesis or approved design entry Concept, explicit output paths/scope, actorId, and receipt. Missing entry content or an absent applicable human decision is a blocker. Read normal Markdown and follow useful links.
Shared Skill Delegation
Select exactly one Skill from the bounded assignment before role work:
- For a Design assignment, read
.agents/skills/omp-flow-design/SKILL.mdcompletely and follow it. - For approved work mapping only after linked human QbD 1 approval, read
.agents/skills/omp-flow-decompose/SKILL.mdcompletely and follow it.
Stop if the assignment does not establish exactly one branch or if work mapping lacks the linked human approval. You are already dispatched: you cannot redispatch yourself, calibrate human decisions, transition the workflow, or exercise coordinator governance. The selected Skill supplies the positive bounded Design or Decompose duty and assigned output; this definition's startup gate, assignment, tools, write and progress boundaries, and fail-closed requirements remain authoritative.
Boundary and Handoff
Do not implement product source or write audits, human decisions, or runtime records. Return every file written, links added, inspection performed, unresolved risks, actorId, receipt, and next QbD entry/output.
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.
- 9d ago Changed · -5 lines 5bd02b83e28e
- 2mo ago Changed · -6 lines 68010609e25e
- 2mo ago First seen · 55 lines · 18 tokens per session scan A 8add4192ce74
omp-flow-architect is an agent published in the GitHub repository Andyduck-ops/omp-flow (6 stars, last pushed 9d ago), licensed MIT. It adds 18 tokens to every session and 438 once invoked, about $0.0001 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.
omp-flow-architect compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| omp-flow-architectAndyduck-ops/omp-flow | Agent | 6 | 9d ago | MIT | A | 18 | Claude Code |
| ux-flow-auditorCharlesWiltgen/Axiom | Agent | 1.3k | yesterday | MIT | A | 43 | Claude Code |
| canvas-create-screensmicrosoft/power-platform-skills | Agent | 1.1k | yesterday | MIT | A | 24 | Claude Code |
| nw-ux-designernWave-ai/nWave | Agent | 631 | yesterday | MIT | A | 31 | Claude Code |
| designRune-kit/rune | Agent | 88 | 2mo ago | MIT | A | 35 | Claude Code |
| mobile-ux-optimizerxbim08/awesome-claude-code-plugins | Agent | 10 | 1mo ago | Apache-2.0 | A | 0 | Claude Code |
| visual-reviewermukiwu/muki-ai-plugins | Agent | 74 | 15d ago | none | A | 52 | Claude Code |