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 adaptyteam/adapty-skills --skill flow-generatorgit clone --depth 1 https://github.com/adaptyteam/adapty-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/adaptyteam/adapty-skills/flow-generator)<a href="https://agentmods.dev/skills/adaptyteam/adapty-skills/flow-generator"><img src="https://agentmods.dev/badge/skills/adaptyteam/adapty-skills/flow-generator/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/adaptyteam/adapty-skills/flow-generator"><img src="https://agentmods.dev/badge/skills/adaptyteam/adapty-skills/flow-generator.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 | $0.00218 | $0.20355 |
| Opus 5.5 | $0.00087 | $0.08142 |
| Sonnet 5.5 | $0.00044 | $0.04071 |
| Haiku 4.5 | $0.00022 | $0.02036 |
Grade A, and why
flow-generator 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 today.
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 — 1,230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flow generator
Read an Adapty flow's builder config, transform it, check the result, and write it back. Transforming a config that exists is the default, and the safer path: everything you emit is then grounded in a document that already works.
Authoring a new flow is also in scope, and two things — and only these two — genuinely cannot be synthesized:
- An image you have no readable FILE for. Given a path you can now upload it —
flows media upload(media.md). An image you can only see — pasted or attached into the conversation — is not one you have: ask for a path. With no file there is nothing to upload, so its catalog entry stays empty, never a made-up URL (trap 5). SVG uploads fail, so a monochrome glyph is authored inline in_meta.icons; a graphic no element can express, you draw and rasterize (media.md). An icon is not in this list:python3 references/icons.py --search <word>resolves any phosphor glyph, and an invented name draws blank however good your markup is (trap 23). - Real store prices. They come from the store, not from Adapty;
products createhas no price flag.
Everything else is reachable: product UUIDs from adapty products list (or products create),
theme colours sampled off a reference screenshot, and icon markup resolved from the bundle
references/icons.py ships.
flowProductId — the per-screen declaration in _meta.screens[].products[] — is derived, not
waited for. flowkit.predeclare(screen_id, products) writes the block; pass exact Product + Offer
pairs, a bare product id or a (product_id, offer_id) tuple, because the offer is part of the id.
Omit the declaration and device preview 422s. When rewriting a flow, carry the live
_meta.screens forward instead of regenerating it — and screens[].products with it, the
screen-owned registry that _meta is derived from. Never write "products": []: absent and empty
mean opposite things to the builder. When authoring, flowkit.screen() writes the registry and
the structured product refs for you, from the screen's own bindings — bind an offer with
product(..., offer_id=...) and a dotted price variable picks it up
(products.md).
When you do author, references/flowkit.py owns the mechanical parts —
the hierarchy/map split above all — and patterns.md owns the shapes.
It also covers conditions (when/ref/all_/not_empty), all fourteen action types, the
eight inputs and the tabs composite — each raising on the shape the transform service refuses.
What ships with it
30 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/canvas.py 29 KB runs code
- references/component-catalog.json 775 KB
- references/crop.py 13 KB runs code
- references/custom-icons.json 8.1 KB
- references/diff-config.py 18 KB runs code
- references/fidelity.md 11 KB
- references/flow-schema.md 150 KB
- references/flowkit.py 155 KB runs code
- references/gates.sh 7.6 KB runs code
- references/icons.py 9.3 KB runs code
- references/localization.py 30 KB runs code
- references/media.md 32 KB
- references/merge.md 12 KB
- references/mobile-preview.mjs 13 KB runs code
- references/montage.py 5.8 KB runs code
- references/patterns.md 86 KB
- references/phosphor-icons.json.gz 483 KB
- references/placements.md 8.8 KB
- references/preview-with-playwright.mjs 6.6 KB runs code
- references/preview.md 39 KB
- references/products.md 33 KB
- references/rename-screens.py 9.0 KB runs code
- references/render-measure.py 13 KB runs code
- references/shoot.sh 18 KB runs code
- references/snippet.py 72 KB runs code
- references/snippets.md 21 KB
- references/transforms.md 25 KB
- references/validate-with-schema.mjs 12 KB runs code
- references/validate.md 15 KB
- references/verify-config.py 194 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.
- today Changed · +14 lines cfea9ea78603
- 4d ago Changed · +28 lines 3a1fc6f535c7
- 6d ago Changed · +7 lines 801748769491
- 7d ago Changed · +105 lines · +13 tokens per session a4670c4f5066
- 10d ago Changed · +10 lines 043ae0d91b57
- 11d ago Changed · -21 lines 9dd0a63b8d26
- 13d ago Changed · +23 lines · +23 tokens per session ca783c8ab500
- 17d ago Changed 1c411ff2d888
- 19d ago Changed · +63 lines bb72458337eb
- 20d ago First seen · 1,001 lines · 182 tokens per session scan A e2e8b9b8928f
flow-generator is a skill published in the GitHub repository adaptyteam/adapty-skills (6 stars, last pushed today), licensed MIT. It adds 218 tokens to every session and 20,355 once invoked, about $0.0009 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.
Other skills, from other repositories
flutter-setup-localization
Add flutterlocalizations and intl dependencies, enable "generate true" in pubspec.yaml, and create an l10n.yaml configuration file. Use when initializing localization support for a new Flutter project.
asc-localize-metadata
Automatically translate and sync App Store metadata (description, keywords, what's new, subtitle) to multiple languages using LLM translation and asc CLI. Use when asked to localize an app's App Store listing, translate app descriptions, or add new languages to App Store Connect.
asc-metadata-sync
Sync, validate, and apply App Store metadata and store assets with asc. Use when updating localizations, keywords, App Clip or preview assets, Asset Library media and placements, or migrating legacy fastlane metadata.
asc-in-app-events
Create and localize App Store in-app events, upload event media, and submit or recover event review submissions with asc. Use when managing in-app events, event card or details page assets, or event-specific submission errors.
maui-localization-theming
Implement MAUI localization and theming. USE FOR: RESX/AppResources, runtime culture switching, RTL/FlowDirection, platform language metadata, AppThemeBinding, DynamicResource, light/dark/system themes, UserAppTheme. DO NOT USE FOR: general layout, accessibility audits, icon/splash assets.
android-resources
Organize Android strings, drawables, fonts, themes, localization, and concrete resource-backed Compose values such as MaterialTheme colors. Use for resource declarations and their direct UI lookup; defer design-system token architecture, network image loading, lint-rule configuration, and general Compose…