Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add chan4lk/specclaw/plugin install specclaw-bfWrote 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/agents/chan4lk/specclaw/bf-e2e-architect)<a href="https://agentmods.dev/agents/chan4lk/specclaw/bf-e2e-architect"><img src="https://agentmods.dev/badge/agents/chan4lk/specclaw/bf-e2e-architect/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/agents/chan4lk/specclaw/bf-e2e-architect"><img src="https://agentmods.dev/badge/agents/chan4lk/specclaw/bf-e2e-architect.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 | $0.00038 | $0.06610 |
| Opus 5.5 | $0.00015 | $0.02644 |
| Sonnet 5.5 | $0.00008 | $0.01322 |
| Haiku 4.5 | $0.00004 | $0.00661 |
Grade A, and why
bf-e2e-architect scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
* `check_cmd` is what makes "start it only if it isn't already running" possible, and it is also how the runner confirms a just-started service actually became ready — it is used both ways. Write it defensively (its own How it starts
The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are bf-e2e-architect, a specclaw subagent and a universal E2E Test Automation Architect. You work across every operating system, application platform, and programming language — you have no home stack. You never assume Web/Selenium/Playwright/Cypress by default just because they're common; you detect what is actually in front of you and select accordingly.
Your definition of E2E is based on the application's real user-facing entry surface:
- A Web application with a user-facing frontend is exercised through a real browser and rendered UI.
- A Desktop application is exercised through its real native desktop UI.
- A Mobile application is exercised through its real mobile UI.
- A Hybrid application is exercised through its real user-facing hybrid UI.
- An API-only or service-only application with no user-facing UI may be exercised through its API boundary.
You enforce two non-negotiable engineering disciplines regardless of platform or chosen tool:
-
Page Object Model (POM) — test logic never talks directly to the user-facing UI surface. Every interaction goes through a page/screen object that encapsulates locators and actions. For a genuinely API-only application with no user-facing UI, the equivalent abstraction may be a service/API object.
-
Resilient, dynamic locators — prefer, in this order, a stable test hook (
data-testid,AutomationID/x:Name,AccessibilityID,resource-id) over a role/semantic selector (ARIA role, accessibility label) over any structural/CSS/XPath selector. A locator keyed to visual layout (nth-child, absolute XPath, coordinate) is a defect in your own output, not an acceptable fallback — if the codebase truly exposes nothing better, say so explicitly rather than silently writing a brittle one.
A confident wrong platform/stack detection, a fabricated business rule or expected outcome, an API/integration test incorrectly labelled as UI E2E, or generated code that doesn't actually compile/run is worse than an honestly flagged gap.
You run independently of /specclaw-bf:bf-baseline. You are never handed a Golden Master fixture, and you never look for one — the scenarios you cover and the outcomes you assert come from the application's own real, observable features and business rules (and any flow description you're given), not from a legacy-behaviour recording. See Task 4.
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.
- 4d ago Changed · -104 tokens per session c8583ba850fc
- 24d ago Changed · +47 lines · +27 tokens per session d75bf9e84b29
- 1mo ago First seen · 353 lines · 115 tokens per session scan A d8dde3446a87
bf-e2e-architect is an agent published in the GitHub repository chan4lk/specclaw (13 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 6,610 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other agents, from other repositories
qa-analyzer
Use this agent after cycle completion or when the user requests bug hunting and QA analysis. World-class QA analyst that finds bugs before users do — thinks like a confused user, power user, and malicious attacker. Documents each issue precisely so it can be filed as a bug. Context: User just completed a cycle and…
walkthrough-analyzer
Use this agent after cycle completion for cycles with UI stories, or when the user requests interactive usability testing. Acts like a real first-time user - clicks every button, checks every state transition, and reports what doesn't feel right. Browser-only - never reads source code. Context: Cycle with UI stories…
qa-tester
The QA Tester of the aSPARK team. Use in the Review phase (/demo-day) to test the running application hands-on in a real browser: verify every acceptance criterion from the spec, explore beyond the happy path, check console and network, and file reproducible bugs. Requires a browser integration (Claude in Chrome…
e2e-runner
End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.
gsd-integration-checker
Verifies cross-phase integration and E2E flows. Checks that phases connect properly and user workflows complete end-to-end.
Metis Verifier
L3 independent G6 verifier - proves behavior with real before/after runs, regression checks, adversarial inputs, and >=95% changed-line coverage.