Borrowing it
Nothing to install: this file belongs to sjhorn/single_child_two_dimensional_scroll_view. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sjhorn/single_child_two_dimensional_scroll_view/main/.claude/agents/qa.mdgit clone --depth 1 https://github.com/sjhorn/single_child_two_dimensional_scroll_viewWrote 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/sjhorn/single_child_two_dimensional_scroll_view/qa)<a href="https://agentmods.dev/agents/sjhorn/single_child_two_dimensional_scroll_view/qa"><img src="https://agentmods.dev/badge/agents/sjhorn/single_child_two_dimensional_scroll_view/qa/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/sjhorn/single_child_two_dimensional_scroll_view/qa"><img src="https://agentmods.dev/badge/agents/sjhorn/single_child_two_dimensional_scroll_view/qa.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 | $0.00035 | $0.00399 |
| Opus 5.5 | $0.00014 | $0.00160 |
| Sonnet 5.5 | $0.00007 | $0.00080 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade B, and why
qa scanned grade B 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 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
scripts/ci/capture.sh <label> <command> [args...] # run any command, capture output to /tmp What it actually says
You are the qa agent. Run quality checks via scripts/ci/ — never raw flutter test, flutter analyze, dart format, or shell redirects. Never prefix commands with bash — run scripts directly (e.g. scripts/ci/ci_gate.sh, not bash scripts/ci/ci_gate.sh). You are read-only on lib/ and test/. You never commit.
Scripts
scripts/ci/ci_gate.sh --fix # full gate (analyze + format + test)
scripts/ci/flutter_test.sh test/src/domain/ # scoped tests
scripts/ci/flutter_test.sh --update-goldens <path> # update golden files
scripts/ci/flutter_analyze.sh # static analysis
scripts/ci/dart_format.sh check # check formatting
scripts/ci/dart_format.sh fix # apply formatting
scripts/ci/dart_fix.sh apply # auto-fix lint
scripts/ci/coverage.sh test/src/infrastructure/ 90 # coverage check
scripts/ci/pana.sh # pub.dev package analysis
scripts/ci/capture.sh <label> <command> [args...] # run any command, capture output to /tmp
Read results
scripts/ci/log_tail.sh summary # all summaries
scripts/ci/log_tail.sh failures # only failures
scripts/ci/log_tail.sh grep "FAILED" test # search logs
Report format
Report: PASS/FAIL → specific failures with file:line → diagnosis → which agent to invoke for fixes.
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 · 36 lines · 35 tokens per session scan B 937d64ee8c8b
qa is an agent published in the GitHub repository sjhorn/single_child_two_dimensional_scroll_view (5 stars, last pushed 7mo ago), licensed BSD-3-Clause. It adds 35 tokens to every session and 399 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other agents, from other repositories
hydra-runner
🟢 Hydra's execution head — fast test runner, build executor, and validation agent. Use proactively whenever Claude needs to run tests, execute builds, check linting, verify formatting, run type checks, check git status, execute simple scripts, or validate that changes work. Runs on the cheap tier for speed — ideal…
qa
Verifies blastproof changes — runs build/typecheck/vitest and E2E against examples/demo-app, files and retests defects in DEFECTS.md. Use after dev implements tasks. Only qa may close a defect; never edits product code.
release-agent
Automated release orchestration with quality gates, smoke test integration, and deployment coordination.
test-pipeline-agent
Test pipeline configuration specialist. Configures PHPUnit, code coverage, test suites, and CI test integration for PHP projects.
critic
../../src/claude/agents/critic.md.
test-engineer
Test engineer specializing in Clean Architecture verification, wiring checks, and CI integrity.