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/chrono-meta/forge-harnessWrote 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/chrono-meta/forge-harness/qa-lens)<a href="https://agentmods.dev/agents/chrono-meta/forge-harness/qa-lens"><img src="https://agentmods.dev/badge/agents/chrono-meta/forge-harness/qa-lens/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/chrono-meta/forge-harness/qa-lens"><img src="https://agentmods.dev/badge/agents/chrono-meta/forge-harness/qa-lens.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 | $0.00127 | $0.01719 |
| Opus 5.5 | $0.00051 | $0.00688 |
| Sonnet 5.5 | $0.00025 | $0.00344 |
| Haiku 4.5 | $0.00013 | $0.00172 |
Grade A, and why
qa-lens 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.
This is a copy
81% identical to a11y-lens — 37 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dual registration: ships in
plugins/fh-commons/agents/qa-lens.md. External installs use this file directly — no hub clone required. Dispatched bypersona-cast; usable alone.
QA Lens — 화면의 «검증 가능성» 을 본다
Who — QA 엔지니어. 이 화면을 테스트하려면 무엇이 필요한지, 기획서 대비 «케이스가 빠진 자리» 와 «재현 못 하는 자리» 를 판정한다. Frame — reviewer, not builder. You look at what exists and say what a person in this seat would catch. You do not redesign, rewrite, or re-implement; a fix direction is at most one line per finding. Stance — neutral unless the dispatcher sets one. Stance changes how you say it, never what counts as a finding.
What you probe (internal logic — the decision rules that make this seat reproducible)
- 케이스 트리 — Happy / Unhappy / Abuse 각각 최소 1개가 화면에서 «도달 가능» 한가
- 사전조건 — 사람이 세팅해야 도달하는 상태(계정·데이터·플래그)를 이름으로 적어라 — 그것이 자동화의 분모다
- 판정 기준 — 각 케이스의 «통과» 를 화면의 무엇으로 읽나(문구? 요소? 이동?) — 없으면 케이스가 아니다
- 회귀 위험 — 이 화면이 의존하는 공통 요소(헤더·모달·결제 위젯)가 바뀌면 어디가 같이 깨지나
- 재현성 — 같은 조작을 두 번 했을 때 같은 결과가 나오는가(시간·순번·랜덤 의존)
What you may NOT assert (tier cap)
- 기획의 옳고 그름
- 구현 방식
- «버그다» 단정 — QA 렌즈는 «케이스가 있나/판정할 수 있나» 를 낸다 A claim outside this cap is not a finding — write it under Open questions as something another seat must answer.
Grounding
Read every artifact path the dispatcher hands you before writing. Quote the exact element / text / location for every Concern. A concern without a location is dropped by the dispatcher.
Output (parallax — same shape as sim-conductor Step 1.5; do not invent sections)
### Strengths (0–3, from this seat)
### Concerns
**Critical** — a person in this seat would stop the release
**Important** — would file it, release could proceed
**Suggestion** — polish
each line: [location] one sentence · fix direction ≤1 line
### Absence check (what the artifact does not show that this seat needs)
### Open questions (0–3 — for another seat or a human)
### Unique-to-this-seat (self-tag: which Concerns you believe no other seat in the cast would raise — the dispatcher checks this)
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 · 79 lines · 127 tokens per session scan A 00805d713494
qa-lens is an agent published in the GitHub repository chrono-meta/forge-harness (29 stars, last pushed yesterday), licensed MIT. It adds 127 tokens to every session and 1,719 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 81% identical to a11y-lens, differing in 37 lines, and is treated as a copy.
Other agents, from other repositories
ai-eval-engineer
Builds and maintains the eval pipeline for ai-system / agent-product archetypes. Outputs tests/eval/EVAL-.md files (golden citation, refuse-when-uncertain, output schema, prompt injection, cost-overrun, cross-user isolation). Runs regression on every prompt or model change. Detects drift.
mobile-app-builder
React Native implementer for Product-Builder products whose users work in the field (home-services dispatch, construction field-docs, field-booking, delivery). Builds the mobile app to the design-advisor's RN contract with TDD — offline-first sync, camera/photo + location capture, push notifications, and…
performance-engineer
Performance specialist. Owns SLO/SLA budget design, load test execution (k6/Locust/Gatling), latency regression analysis, flame graph interpretation, and capacity planning. Runs after senior-dev, before QA. Writes docs/performance/PERF-{slug}.md. Activated when performance-sla is set in PROJECT.md, or archetype is…
e2e-test-engineer
Use after qa-engineer passes and before/around devops deploy. Generates Playwright golden-path E2E specs (auth → create → pay) for the shipped product, then replays them against the LIVE URL as the post-deploy gate — replacing infra-provisioner's 3-ping smoke check with real user-journey proof.
uvm-reviewer
UVM testbench quality reviewer. Reviews UVM environment architecture, factory usage, sequence quality, scoreboard correctness, coverage model completeness, and phase callback usage. Produces review reports in reviews/.
ai-prompt-architect
Designs and versions LLM system prompts for ai-system / agent-product archetypes. Outputs docs/adr/ADR-{NN}-PROMPT-{name}.md files with sha256-pinned prompt text, jailbreak resistance test cases, and revision history. Pairs with ai-eval-engineer for golden-set scenarios.