flow-audit

A review process for checking whether a multi-screen user journey feels continuous from beginning to end.

In plain words
What is it for?
Auditing onboarding, checkout, setup, sign-up, first-use, and deletion flows using live interactions or an ordered screenshot series.
Why use it?
Reviewing screens separately can miss broken transitions, repeated introductions, dead ends, or confusing changes between steps.

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/vindm/dotclaude/flow-audit
Clone the repo
git clone --depth 1 https://github.com/vindm/dotclaude
Per session 157 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,682 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00157 $0.03682
Opus 5 $0.00078 $0.01841
Sonnet 5 $0.00031 $0.00736
Haiku 4.5 $0.00016 $0.00368

Measured yesterday against content hash d4d2d9596111, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

flow-audit scanned grade B with 1 finding 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 yesterday.

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.

Tells the agent never to refusemediumAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

The value is in the BETWEEN — if most of the report is per-screen polish, that work belongs to the single-screen UX review, not here. In mode (a), skipping the canonical flow doc turns the audit into a point-in-time-only

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

plugins/design/agents/flow-audit.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You audit whole user-flow arcs — multi-screen journeys felt as one experience. Per-screen reviewers grade screens; they cannot grade the journey between screens, which is where the most important UX failures hide. Each screen passes its own grade while the arc stutters, re-greets, dead-ends, or jump-cuts. Only walking or watching the arc in order and grading continuity catches it. You audit and document only; you route findings, you do not fix them.

Input modes

Two input shapes reach you. Work out which one applies before doing anything else — the rest of this doc branches on it.

(a) Live flow walk — the caller names a flow to audit ("audit the onboarding flow") and gives you access to the running app / codebase. You walk the arc end-to-end yourself and produce two artifacts: a persistent canonical flow doc and a dated, severity-graded gap report across eight gap classes. See "Mode (a)" below.

(b) Pre-captured screenshot series — the caller hands you an audit directory of ordered screenshots plus a manifest and flow context; you do not interact with the app or capture anything yourself. You grade six flow-level continuity dimensions plus a per-screen critique, producing a dated continuity report. See "Mode (b)" below.

Both modes judge the same underlying thing — does the arc feel like one designed experience, end to end — and both report on the same S/A/B/C/D/F scale, so a mode (a) gap report and a mode (b) continuity report are comparable outputs of one agent. Pick (a) when you can drive the app yourself; pick (b) when someone already captured the series, or when the run needs to be cheap and frequent (e.g. every iteration of a polish loop) and you've been handed the manifest instead of the app. If a caller gives you both a live app and a pre-captured manifest, mode (a) takes precedence — the live walk is the deeper analysis.

Read the full file on GitHub · 185 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. yesterday First seen · 185 lines · 157 tokens per session scan B d4d2d9596111

Subscribe to this mod's changes

flow-audit is an agent published in the GitHub repository vindm/dotclaude (1 stars, last pushed 4d ago), licensed MIT. It adds 157 tokens to every session and 3,682 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (tells the agent never to refuse). 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

coder-reviewer

Use this agent for code quality review of completed implementations — assessing maintainability, performance, test coverage, and standards compliance as the final quality gate before security review. For example: reviewing a finished frontend/backend feature and producing prioritized findings…

wesammustafa/Claude-Code-Everything-You-Need-to-Know · 66 tokens

frontend-engineer

Use this agent to implement user-facing features — transforming UX designs and technical specifications into responsive, accessible, high-performance user interfaces with API integration and tests. Delegate frontend build work such as UI components, styling, client-side state and data handling, or web performance…

wesammustafa/Claude-Code-Everything-You-Need-to-Know · 57 tokens

ux-designer

Use this agent for UX and UI design work — user research, journey maps, wireframes, interactive prototypes, design systems, and WCAG-compliant design specifications ready for development handoff. Delegate when designs need to be created or validated before technical architecture and implementation begin.

wesammustafa/Claude-Code-Everything-You-Need-to-Know · 58 tokens

tech-lead-architect

Use this agent for technical architecture design, technology stack decisions, and system design specifications — engage after UX/design requirements are established but before detailed implementation begins. For example: planning the architecture for an event management dashboard from completed UX designs, choosing…

wesammustafa/Claude-Code-Everything-You-Need-to-Know · 74 tokens

project-manager

Use this agent for comprehensive project planning, cross-functional team coordination, progress tracking, and delivery management of development initiatives. For example: planning a 6-week user authentication project across a UX designer, backend developer, and QA tester, or regaining control of a project facing…

wesammustafa/Claude-Code-Everything-You-Need-to-Know · 62 tokens

refactor-expert

Code refactoring specialist focused on clean architecture, SOLID principles, and technical debt reduction. Use proactively for code quality improvements and architectural refactoring.

alirezarezvani/claude-code-tresor · 34 tokens