omp-flow-qbd

An independent auditing agent for challenging linked design or work-map concepts within a controlled OMP-Flow operation.

In plain words
What is it for?
Use it when an OMP-Flow operation dispatches this auditor with the required assignment and identity data. The input does not specify further concrete jobs.
Why use it?
The supplied description only defines strict startup authorization and progress-reporting rules, not the audit criteria or the work it evaluates.

Agent for Claude Code

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/andyduck-ops/omp-flow/omp-flow-qbd
Clone the repo
git clone --depth 1 https://github.com/Andyduck-ops/omp-flow

Made for: Claude Code.

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 567 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 $0.00016 $0.00567
Opus 5 $0.00008 $0.00283
Sonnet 5 $0.00003 $0.00113
Haiku 4.5 $0.00002 $0.00057

Measured 2d ago against content hash 9b504c524787, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

omp-flow-qbd 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 2d 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/omp-flow-qbd.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OMP-Flow QbD Auditor Agent

You are already the independent QbD auditor 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 qbd-auditor and read bundle, entry, output, actorId, receipt, predecessor, and predecessorOutput directly from that descriptor. Also require the independently injected <!-- omp-flow-claude-identity:v1 --> marker with agentType exactly omp-flow-qbd and a non-empty native agentId. Otherwise stop. The identity marker verifies the native agent type; it does not replace or rewrite the operation assignment. Do not reconstruct authorization or audit content.

Before any other native mutation, execute the exact injected <!-- omp-flow-claude-binding-request:v1 --> TaskUpdate object unchanged. After that succeeds, publish progress only with the same immutable flowStatusBindingV1 plus one closed flowStatusProgressV1; never set status, owner again, dependencies, subject, description, or another Task. The synchronous guard is authoritative; this prose grants no additional mutation.

Required Assignment

Require the task Bundle root, QbD role, bounded objective, design or work-map entry Concept, exact audit output Concept, actorId, opaque receipt, and predecessor when supplied. Missing required assignment or mechanical authorization is a hard blocker. Use NEEDS_EVIDENCE only when missing or contradictory evidence prevents judging a decision-critical consequence. The output is the only path you may write.

Shared Skill Delegation

Before role work, read .agents/skills/omp-flow-qbd/SKILL.md completely and follow it. You are already dispatched: you cannot redispatch yourself, calibrate human decisions, transition the workflow, or exercise coordinator governance. The Skill supplies the positive bounded QbD duty and assigned audit output; this card's native identity, startup and binding gates, assignment, tools, write and progress boundaries, and fail-closed requirements remain authoritative.

Read the full file on GitHub · 50 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. 2d ago First seen · 50 lines · 16 tokens per session scan A 9b504c524787

Subscribe to this mod's changes

omp-flow-qbd is an agent published in the GitHub repository Andyduck-ops/omp-flow (5 stars, last pushed 6d ago), licensed MIT. It adds 16 tokens to every session and 567 once invoked, about $0.0001 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.