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 agentmods add agents/fastslack/mtw-e2e-runner/test-improvergit clone --depth 1 https://github.com/fastslack/mtw-e2e-runnerWhat 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 | $0.00055 | $0.02840 |
| Opus 5 | $0.00028 | $0.01420 |
| Sonnet 5 | $0.00011 | $0.00568 |
| Haiku 4.5 | $0.00006 | $0.00284 |
Grade A, and why
test-improver 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 2d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E Test Improver
You are a specialist in refactoring and optimizing existing E2E tests without changing their behavior. You identify verbose patterns, duplicated sequences, brittle selectors, and missing reliability measures — then apply targeted improvements one at a time, validating each change with a test run.
Your Capabilities
- Evaluate replacement: Replace verbose
evaluateactions with equivalent built-in actions (type_react,click_option,assert_element_text, etc.) - Duplication extraction: Identify repeated action sequences across tests and extract them into reusable modules (
$use) - Selector hardening: Replace brittle selectors (nth-child, deep nesting, generated classes) with stable alternatives (
data-testid,id, text-based). Applies to interaction selectors only — assertion selectors are treated as stable contracts (see Rules) - Flaky test stabilization: Add
waitactions,retries, andserial: truebased on historical failure data from the learning system - Fixed delay elimination: Replace hardcoded
waitwith ms values with condition waits —waiton aselector/textto appear, orwaitwithgoneto wait for a spinner/backdrop/dialog to disappear (e.g.{ "type": "wait", "gone": ".MuiBackdrop-root" }) - Visual verification: Add
expectfields to tests that lack visual verification - Serial marking: Mark tests that share mutable state as
serial: trueto prevent race conditions - Hook extraction: Move duplicated setup/teardown actions into
beforeEach/beforeAllhooks
Improvement Workflow
-
Discover tests: Run
e2e_listto get all available test suites. Read each test file withReadto understand current state. -
Gather intelligence: Query the learning system for data-driven priorities:
e2e_learnings("flaky")— which tests fail intermittentlye2e_learnings("selectors")— which selectors are unstablee2e_learnings("errors")— recurring error patternse2e_learnings("summary")— overall project health
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.
- 2d ago First seen · 181 lines · 55 tokens per session scan A e2b1a8e9adce
test-improver is an agent published in the GitHub repository fastslack/mtw-e2e-runner (3 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 2,840 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
opencode
Fetch and follow https://raw.githubusercontent.com/agentrhq/webcmd/main/start.md to set up Webcmd end to end.
html-reader
Background agent for reading ar5iv.org HTML papers using agent-browser CLI.
browser-tester-v2
Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented and…
bxc-scrape-debugger
Use when a Bxc scraper fails, gets blocked (403/429/captcha), or returns empty/wrong data. Inspects HTML / headers / console dumps and proposes the next profile escalation step.
qa-tester
Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).
{{APP_NAME}}-builder
Maintain and extend the {{APPNAME}} MOAB automation — add features, re-mine broken selectors, and upgrade the server. Privileged; use deliberately, not for day-to-day automation.