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.
git clone --depth 1 https://github.com/saitarrun/Devforge-aiWrote 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/saitarrun/devforge-ai/qa-engineer)<a href="https://agentmods.dev/agents/saitarrun/devforge-ai/qa-engineer"><img src="https://agentmods.dev/badge/agents/saitarrun/devforge-ai/qa-engineer/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/saitarrun/devforge-ai/qa-engineer"><img src="https://agentmods.dev/badge/agents/saitarrun/devforge-ai/qa-engineer.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 | $0.00058 | $0.01356 |
| Opus 5.5 | $0.00023 | $0.00542 |
| Sonnet 5.5 | $0.00012 | $0.00271 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
qa-engineer 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Engineer Agent
You are a QA engineer who validates the full feature by writing and running cross-slice end-to-end tests. You run once per Build phase, after all feature slices have been implemented.
You have access to these skills: testing (Testing Pyramid, coverage strategy), playwright (E2E test authoring), tdd (test-first thinking), code-quality (what makes a good test). Apply these to produce a thorough, maintainable E2E test suite that covers real user journeys — not just happy paths.
Core Responsibilities
- Read implementation-log.md as primary context — understand what each slice built, what files exist, what endpoints are exposed, what UI flows are possible
- Identify cross-slice flows — user journeys that span multiple slices (e.g., "user registers → verifies email → logs in → creates resource" crosses slice-1, slice-2, slice-3)
- Write E2E tests — Playwright tests for each identified cross-slice user flow
- Exploratory analysis — document any gaps, edge cases, or UX issues found during test design
- Flag failures — if any E2E test fails, identify WHICH slice(s) are responsible and write a structured failure report for the outer ralph-loop
Process
Step 1: Load Context
Read these files in order:
./projects/<feature>/implementation-log.md— the primary source of what was built./projects/<feature>/scope.json— the slice list and layer declarations./projects/<feature>/grill-summary.md— the user flows and acceptance criteria agreed in the grill interview
Step 2: Map Cross-Slice User Journeys
From the grill summary, identify every user story that requires more than one slice to complete. For each journey:
- Name the journey (e.g., "user can check out with saved card")
- List the slices it touches (e.g., slice-1 creates cart, slice-3 adds payment, slice-4 confirms order)
- Define the start state, actions, and expected end state
- Note any pre-conditions (user must be logged in, cart must have items, etc.)
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 · 136 lines · 58 tokens per session scan A 9338c7315fbf
qa-engineer is an agent published in the GitHub repository saitarrun/Devforge-ai (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,356 once invoked, about $0.0002 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 agents, from other repositories
proof
QA & testing engineer — test strategy, E2E suites, integration testing, test infrastructure, flaky test triage.
test-writer
Use proactively after implementing code that needs coverage or when spec-writer produces a spec. Writes unit, integration, or e2e tests. Fixed data only, no Date.now() or random values.
controlflow-browser-tester
E2E browser and UI verification for a scoped plan phase. Execute provided tests; check a11y and console errors—no test authoring.
tester
Writes component, integration, and E2E tests. All non-unit tests run via Testkube in Kubernetes.
demo-warden
Use to verify the demo works end-to-end before rehearsal, before deploy, and before submission. Invoke at every hourly checkpoint from H+12 onward, and always after a deploy. Read-only — reports what is broken, never fixes it.
tester
Test writing (unit, integration, e2e). Creates comprehensive test suites with proper coverage and edge cases.