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 timoshinoleg-eng/1c-ai-workbench --skill web-testgit clone --depth 1 https://github.com/timoshinoleg-eng/1c-ai-workbenchWrote 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/timoshinoleg-eng/1c-ai-workbench/web-test)<a href="https://agentmods.dev/skills/timoshinoleg-eng/1c-ai-workbench/web-test"><img src="https://agentmods.dev/badge/skills/timoshinoleg-eng/1c-ai-workbench/web-test/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/timoshinoleg-eng/1c-ai-workbench/web-test"><img src="https://agentmods.dev/badge/skills/timoshinoleg-eng/1c-ai-workbench/web-test.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 | $0.00044 | $0.07572 |
| Opus 5 | $0.00022 | $0.03786 |
| Sonnet 5 | $0.00009 | $0.01514 |
| Haiku 4.5 | $0.00004 | $0.00757 |
Grade A, and why
web-test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
86% identical to web-test — 48 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 589 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/web-test — Browser automation for 1C web client
Automates user interactions with 1C:Enterprise web client via Playwright — navigating sections, filling forms, reading tables and reports, filtering lists.
Quick start
RUN="${CLAUDE_SKILL_DIR}/scripts/run.mjs"
# One-shot: opens browser → runs script → closes browser → exits
node $RUN run http://localhost:8081/bpdemo test-scenario.js
# Or pipe inline:
cat <<'SCRIPT' | node $RUN run http://localhost:8081/bpdemo -
await navigateSection('Продажи');
await openCommand('Заказы клиентов');
await clickElement('Создать');
await fillFields({ 'Клиент': 'Альфа' });
await clickElement('Провести и закрыть');
SCRIPT
Setup (first time)
cd "${CLAUDE_SKILL_DIR}/scripts" && npm install
Requires Node.js 18+. npm install downloads Playwright and Chromium.
URL resolution
Read .v8-project.json from project root. Each database has id and optional webUrl.
Construct URL as http://localhost:8081/<id> or use webUrl if set.
Use /web-publish first if the database is not published.
Execution modes
Autonomous mode (preferred for complete scenarios)
node $RUN run <url> script.js # exits when done, no session
Interactive mode (step-by-step development)
# 1. Start session (run_in_background=true, prints JSON when ready)
node $RUN start <url>
# 2. Execute scripts against running session
cat <<'SCRIPT' | node $RUN exec -
const form = await getFormState();
console.log(JSON.stringify(form, null, 2));
SCRIPT
# 2b. Execute without video recording (for debugging/testing)
cat script.js | node $RUN exec - --no-record
# 2c. Override exec HTTP timeout (default 30 min). Use for long scripts
# such as multi-block recordings + addNarration.
cat script.js | node $RUN exec - --timeout-min=120
cat script.js | node $RUN exec - --timeout=7200000
WEB_TEST_EXEC_TIMEOUT_MS=7200000 node $RUN exec script.js
# 3. Screenshot
node $RUN shot result.png
# 4. Stop (logout + close)
node $RUN stop
What ships with it
60 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.
- .gitignore 56 B
- recording.md 15 KB
- regress.md 21 KB
- scripts/browser.mjs 3.2 KB runs code
- scripts/cli/commands/exec.mjs 1.3 KB runs code
- scripts/cli/commands/run.mjs 764 B runs code
- scripts/cli/commands/shot.mjs 638 B runs code
- scripts/cli/commands/start.mjs 1000 B runs code
- scripts/cli/commands/status.mjs 485 B runs code
- scripts/cli/commands/stop.mjs 555 B runs code
- scripts/cli/commands/test.mjs 20 KB runs code
- scripts/cli/exec-context.mjs 5.2 KB runs code
- scripts/cli/server.mjs 1.3 KB runs code
- scripts/cli/session.mjs 724 B runs code
- scripts/cli/test-runner/assertions.mjs 2.9 KB runs code
- scripts/cli/test-runner/discover.mjs 1.7 KB runs code
- scripts/cli/test-runner/reporters.mjs 4.6 KB runs code
- scripts/cli/test-runner/severity.mjs 2.6 KB runs code
- scripts/cli/util.mjs 4.0 KB runs code
- scripts/dom.mjs 2.4 KB runs code
- scripts/dom/_shared.mjs 22 KB runs code
- scripts/dom/edd.mjs 4.2 KB runs code
- scripts/dom/edit-state.mjs 2.0 KB runs code
- scripts/dom/errors-stack.mjs 2.6 KB runs code
- scripts/dom/errors.mjs 6.4 KB runs code
- scripts/dom/filter.mjs 8.3 KB runs code
- scripts/dom/form-state.mjs 1.4 KB runs code
- scripts/dom/forms.mjs 31 KB runs code
- scripts/dom/grid-edit.mjs 14 KB runs code
- scripts/dom/grid.mjs 44 KB runs code
- scripts/dom/nav.mjs 3.9 KB runs code
- scripts/dom/submenu.mjs 7.7 KB runs code
- scripts/engine/core/click.mjs 6.0 KB runs code
- scripts/engine/core/clipboard.mjs 3.6 KB runs code
- scripts/engine/core/errors.mjs 12 KB runs code
- scripts/engine/core/helpers.mjs 6.3 KB runs code
- scripts/engine/core/scroll-horiz.mjs 2.0 KB runs code
- scripts/engine/core/session.mjs 15 KB runs code
- scripts/engine/core/state.mjs 6.6 KB runs code
- scripts/engine/core/wait.mjs 4.0 KB runs code
- scripts/engine/forms/click-form.mjs 5.7 KB runs code
- scripts/engine/forms/click-popup.mjs 4.3 KB runs code
- scripts/engine/forms/close.mjs 2.4 KB runs code
- scripts/engine/forms/fill.mjs 7.6 KB runs code
- scripts/engine/forms/select-value.mjs 54 KB runs code
- scripts/engine/forms/state.mjs 1.4 KB runs code
- scripts/engine/nav/navigation.mjs 10 KB runs code
- scripts/engine/recording/captions.mjs 12 KB runs code
- scripts/engine/recording/capture.mjs 8.6 KB runs code
- scripts/engine/recording/highlight.mjs 16 KB runs code
- scripts/engine/recording/narration.mjs 8.2 KB runs code
- scripts/engine/recording/tts.mjs 6.8 KB runs code
- scripts/engine/spreadsheet/spreadsheet.mjs 22 KB runs code
- scripts/engine/table/click-cell.mjs 11 KB runs code
- scripts/engine/table/click-row.mjs 4.3 KB runs code
- scripts/engine/table/filter.mjs 11 KB runs code
- scripts/engine/table/grid-toggle.mjs 2.9 KB runs code
- scripts/engine/table/grid.mjs 4.1 KB runs code
- scripts/engine/table/row-fill.mjs 44 KB runs code
- scripts/package-lock.json 1.6 KB
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.
- 7d ago First seen · 589 lines · 44 tokens per session scan A 73fef9560cd7
web-test is a skill published in the GitHub repository timoshinoleg-eng/1c-ai-workbench (0 stars, last pushed 22d ago), licensed MIT. It adds 44 tokens to every session and 7,572 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to web-test, differing in 48 lines, and is treated as a copy.
Other skills, from other repositories
1c-web-test
A browser-testing tool for the 1C:Enterprise web client. It uses Playwright to navigate screens, fill forms, read tables and reports, and apply filters.
1c-web-test
A browser-automation tool for testing the 1C:Enterprise web client. It uses scripted actions to navigate screens, fill forms, read tables and reports, and apply filters.
web-test
A skill for checking a 1C system through its web interface in an interactive browser session.
playwright-test
A skill for creating automated browser tests with Playwright, a tool that checks websites by controlling a real browser. The provided information does not describe its other uses.
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.
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.