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.
npx skills add seb1n/awesome-ai-agent-skills --skill user-flow-mappinggit clone --depth 1 https://github.com/seb1n/awesome-ai-agent-skillsWrote 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/skills/seb1n/awesome-ai-agent-skills/user-flow-mapping)<a href="https://agentmods.dev/skills/seb1n/awesome-ai-agent-skills/user-flow-mapping"><img src="https://agentmods.dev/badge/skills/seb1n/awesome-ai-agent-skills/user-flow-mapping/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/skills/seb1n/awesome-ai-agent-skills/user-flow-mapping"><img src="https://agentmods.dev/badge/skills/seb1n/awesome-ai-agent-skills/user-flow-mapping.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00045 | $0.02338 |
| Opus 5 | $0.00023 | $0.01169 |
| Sonnet 5 | $0.00009 | $0.00468 |
| Haiku 4.5 | $0.00005 | $0.00234 |
Grade A, and why
user-flow-mapping 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 13d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- User Flow Mapping — 91% identical, 4 lines differ
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.
User Flow Mapping
This skill enables the agent to create detailed user flow diagrams that map every step, decision point, error state, and success path a user encounters while completing a task in a product. The agent produces three types of flows — task flows (single path, no decisions), user flows (multiple paths with decision branches), and wire flows (flows annotated with screen wireframes) — using Mermaid diagram syntax for portability. Each flow includes annotations for conversion metrics, drop-off risk points, and optimization opportunities.
Workflow
-
Define the Flow Objective and Scope: Identify the specific user goal being mapped (e.g., "Complete a purchase," "Reset a password"). Determine the entry points — how the user arrives at the start of the flow (direct link, homepage navigation, email CTA, push notification). Establish the success criteria and the scope boundary so the diagram does not expand indefinitely.
-
Identify All Steps and Decision Points: List every screen, action, and system response in sequence. Mark decision points where the user or the system branches (e.g., "Is the user logged in?" or "Did payment succeed?"). Include error states, validation failures, and retry loops. For each step, note whether it is a user action (click, type, swipe) or a system action (redirect, API call, email sent).
-
Map Happy Path First, Then Edge Paths: Draw the ideal path from entry to success first. Then layer in alternative paths: what happens if the user is not logged in, if validation fails, if the session times out, if the payment is declined. Each branch should terminate in either a success state, an error recovery path, or an exit point.
-
Annotate with Metrics and Risk Points: At each step, note the relevant metric: page view count, click-through rate, form completion rate, drop-off percentage. Flag high-friction steps where users are likely to abandon (multi-field forms, account creation walls, payment pages). Suggest specific optimizations for each risk point.
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.
- 13d ago First seen · 162 lines · 45 tokens per session scan A 895cfcb18c0c
user-flow-mapping is a skill published in the GitHub repository seb1n/awesome-ai-agent-skills (179 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 2,338 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
etsy-shop-branding
Shop branding — banner design, logo, brand story, cohesive listing photography, packaging.
brand-assets-setup
Generate and deploy a complete brand asset pack for a Next.js App Router project. Scans the project, prints what to generate with exact specs, then imports and wires everything correctly.
payoff-action-modeling
Model product UI actions from user intent questions after a meaningful outcome, completion, created resource, imported data, uploaded file, synced integration, report, deployment, automation, review state, handoff, or workflow milestone. Use when deciding which actions to show, hide, group, name, prioritize, defer, or…
ui-final-polish
Final visual polish for an existing UI without redesigning it. Use after structure is clear, when asked to improve spacing, alignment, text hierarchy, readability, shadows, highlights, effects, action placement, or overall production feel. For screen structure, layer naming, code handoff, preview scenes, or animation…
figma-pencil-fsd-tailwind4
Convert Figma or Pencil designs into production-ready frontend code using Feature-Sliced Design and Tailwind CSS v4. Use when translating designs into code, extracting tokens, mapping UI to FSD layers (shared / entities / features / widgets / pages / app-shell / app), enforcing Server vs Client boundaries when…
pencil-to-code
Convert Pencil .pen design files and named Pencil node IDs into production frontend code. Use when asked to implement, migrate, reproduce, or refine a Pencil/Figma-like visual design in code, especially for responsive artboards, glassmorphism, typography matching, background image layers, design tokens, or visual…