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 automators-com/flowproof --skill flowproof-configgit clone --depth 1 https://github.com/automators-com/flowproofWrote 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/automators-com/flowproof/flowproof-config)<a href="https://agentmods.dev/skills/automators-com/flowproof/flowproof-config"><img src="https://agentmods.dev/badge/skills/automators-com/flowproof/flowproof-config/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/automators-com/flowproof/flowproof-config"><img src="https://agentmods.dev/badge/skills/automators-com/flowproof/flowproof-config.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 | $0.00106 | $0.01318 |
| Opus 5.5 | $0.00042 | $0.00527 |
| Sonnet 5.5 | $0.00021 | $0.00264 |
| Haiku 4.5 | $0.00011 | $0.00132 |
Grade A, and why
flowproof-config 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
flowproof config
Helps the user configure flowproof's SAP GUI, Fiori, and/or AI authoring
credentials so flowproof record/flowproof run can resolve ${SAP_USER},
${FIORI_PASSWORD}, ${FLOWPROOF_AI_API_KEY}, and the rest of the ${VAR}
references their flows use.
This assumes flowproof is already installed and on PATH (flowproof --version to check). If it isn't, stop and tell the user to install it
first — this skill only configures an existing installation.
1. Work out which profile is needed
flowproof treats SAP GUI, Fiori, and AI authoring as independent profiles, each with its own set of fields — ask if it isn't already obvious from context:
sap— SAP GUI, driven via SAP GUI Scripting. Windows only.fiori— a Fiori launchpad in a browser. Cross-platform.ai— model-assisted authoring (--author llm,author-from-doc, and assisted recording), using Anthropic or OpenAI.
A project can use any combination. If the user's flows reference
${SAP_USER}/${SAP_PASSWORD} they need sap; if they reference
${FIORI_USER}/${FIORI_PASSWORD} they need fiori; if authoring fails
because no model key is configured, they need ai. When unsure, ask.
2. Gather the non-secret fields — never the password
For the chosen profile, ask the user for whichever non-secret fields they want to set (skip ones they don't want to change):
sap: user, client, language, connection (the SAP Logon connection name)fiori: user, client, language, base_url (the launchpad URL)ai: provider (anthropicoropenai), and optionally model only for advanced users
Do not ask for passwords or API keys, and do not accept one if it's
offered in chat. flowproof config sap/fiori/ai can take secrets as
plain CLI flags for scripting, but a value typed into this conversation or
passed on the command line here would land in this session's transcript,
and on many shells, in shell history and briefly in the process list. That
is a strictly worse exposure than the alternative in step 4, which never
touches this conversation at all.
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 · 147 lines · 106 tokens per session scan A e3db2250e1ba
flowproof-config is a skill published in the GitHub repository automators-com/flowproof (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 106 tokens to every session and 1,318 once invoked, about $0.0004 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 2026-09-05.
Other skills, from other repositories
shaft-web-actions
Use when implementing SHAFT WebDriver or Playwright navigation, browser state, element interaction, upload, drag-and-drop, window, cookie, or screenshot behavior.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(usecloud=True)), Playwright, Puppeteer or any CDP client.
agent-browser
Use the agent-browser CLI to exercise web interfaces, inspect rendered accessibility state, verify interactions, and capture screenshots. Use for browser-based UI testing and evidence collection. Do not use as a substitute for deterministic Playwright coverage when an automated regression test is the requested…
web-test
A browser-automation tool for testing the 1C:Enterprise web client. It uses Playwright to navigate sections, fill forms, read tables and reports, and perform user actions in a browser.
self-improve
Use when running ChaosEngine Learning Session self-improve. Harness lessons are GitHub issues only. Product lessons may queue after delivery or on request.
Katalon Studio Testing
Comprehensive testing patterns for Katalon Studio including codeless record-and-playback, Groovy scripted testing, custom keywords, data-driven testing, cross-browser execution, and CI/CD integration with Katalon TestOps.