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 arozumenko/sdlc-skills --skill user-flow-mapsgit clone --depth 1 https://github.com/arozumenko/sdlc-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/arozumenko/sdlc-skills/user-flow-maps)<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/user-flow-maps"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/user-flow-maps/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/arozumenko/sdlc-skills/user-flow-maps"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/user-flow-maps.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 | $0.00175 | $0.01400 |
| Opus 5.5 | $0.00070 | $0.00560 |
| Sonnet 5.5 | $0.00035 | $0.00280 |
| Haiku 4.5 | $0.00017 | $0.00140 |
Grade A, and why
user-flow-maps 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User-flow maps
Turn a flow — screens, decisions, branches, failure paths — into a reviewable HTML poster. The output is one self-contained file per flow plus an index that links them; it opens straight from disk, no server and no network.
The one rule
You supply data. The library supplies every coordinate.
Hand-positioning a flow map is a trap: it looks fine until an edge is added,
then captions collide, arrows point into empty space, and each fix creates the
next one. scripts/flowmap.js owns layout, lane packing, orthogonal routing,
anchor selection and label de-collision. Never write pixel maths in a spec.
Workflow
- Write a spec. One JSON file describing the whole set. See
references/spec-schema.mdfor the contract and a worked example. - Build.
Addnode scripts/build-flowmaps.mjs <spec.json> --out <dir>--layout story [--screens <dir|file>]to build into a shared design-story site instead of a standalone set: pages land in<out>/flows/<slug>.html(one directory deeper than the flat default) so they can sit next to screen-specs'screens/output without a filename collision. When--screenspoints at the matching*.screens.jsonspec(s), every flow node whose id matches a screen'snodebecomes a click-through to that screen's page (../screens/<slug>.html#<screenId>). Omitting--screens(or pointing it at nothing yet built) just renders the flow with no screen links — this build never depends on the other having run first. - Verify before you claim it works. Open the pages and check them — the
library is deterministic but a spec can still describe a flow badly (a
dangling target, a decision with no outcomes).
references/verifying.mdhas a copy-paste browser audit that reports edge/caption collisions, overlapping labels and orphan nodes. Run it. A flow map that looks drawn but routes an arrow through a screen is worse than no diagram.
How ids drive layout
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/example-hotelbooking.flowspec.json 53 KB
- references/spec-schema.md 5.2 KB
- references/verifying.md 5.5 KB
- scripts/__fixtures__/story.flowspec.json 464 B
- scripts/__fixtures__/story.screens.json 333 B
- scripts/build-flowmaps.mjs 16 KB runs code
- scripts/flowmap.js 36 KB runs code
- scripts/package.json 25 B
- scripts/story.test.mjs 3.0 KB runs code
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.
- 1mo ago First seen · 104 lines · 175 tokens per session scan A f4e16b1cf4c2
user-flow-maps is a skill published in the GitHub repository arozumenko/sdlc-skills (25 stars, last pushed yesterday), licensed MIT. It adds 175 tokens to every session and 1,400 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.