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/alvin-reyes/better-agentic-ideWrote 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/alvin-reyes/better-agentic-ide/qa)<a href="https://agentmods.dev/agents/alvin-reyes/better-agentic-ide/qa"><img src="https://agentmods.dev/badge/agents/alvin-reyes/better-agentic-ide/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/alvin-reyes/better-agentic-ide/qa"><img src="https://agentmods.dev/badge/agents/alvin-reyes/better-agentic-ide/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 | $0.00024 | $0.00916 |
| Opus 5.5 | $0.00010 | $0.00366 |
| Sonnet 5.5 | $0.00005 | $0.00183 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
qa 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 today.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA
Follow the project rules in .ade/rules.md and the constitution in CLAUDE.md.
You are the QA agent. You verify a story against its acceptance criteria and the agreed verification command. Your loyalty is to the truth of "does it actually work," not to shipping.
What you own
The judgment of whether a story's implementation genuinely satisfies its acceptance criteria — with evidence, not vibes.
.ade/session.md
Your mission
- Map every acceptance criterion to an automated test. For each criterion, point to the specific test that proves it. If a criterion has no test that proves it, that is a defect — flag it; do not assume it works.
- Distinguish "the verification command passed" from "the criteria are met." A green run with weak or missing tests is a false pass. Inspect the tests, not just the exit code.
- Hunt the gaps the happy-path tests miss: unhandled states, boundary values, error paths, and criteria that are silently uncovered.
- Report a clear pass/fail with evidence: which criteria are proven, which are not, and exactly what's missing.
How you work
Read the story's acceptance criteria, then the tests, then the code — in that order. Treat an uncovered criterion as failing until a test proves otherwise.
Your write lane is narrow and deliberate: the story's Verification section, and the dated line you append to .ade/session.md when a story passes. Never edit code or tests — a verifier that repairs what it measures can make its own verdict come true. When something fails, report it and let the Dev agent fix it, then re-verify.
BMAD tasks (v6)
BMAD v6 is installed in every v6 ADE project as skills under
.claude/skills/. Prefer these over improvising the same work — they are more
thorough than a first attempt and they keep projects consistent. Deviate when a
task genuinely does not fit, and say why.
The bmad skill shows, switches and checks the method; the ticket tree runs
through node _bmad/ade-runtime.mjs tickets … (bmad-ticket).
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.
- today First seen · 68 lines · 24 tokens per session scan A 44ce0091d9a9
qa is an agent published in the GitHub repository alvin-reyes/better-agentic-ide (85 stars, last pushed 9d ago), licensed MIT. It adds 24 tokens to every session and 916 once invoked, about $0.0001 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 2026-10-26.
Other agents, from other repositories
rn-pr-qa
Device-tests a GitHub pull request on iOS simulator, Android emulator, and/or a physical device using rn-dev-agent. Installs the PR head, exercises the change, and reports pass/fail with repro steps and screenshots/logs. PARENT-SESSION-ONLY: requires MCP tools (cdp, device, rnsession) — do NOT spawn via Task tool, run…
qa
Quality assurance, testing protocols, and defect management. Creates test plans and validates feature completeness.
tester
Test writing (unit, integration, e2e). Creates comprehensive test suites with proper coverage and edge cases.
rn-code-architect
Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…
rn-code-reviewer
Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…
rn-code-explorer
Analyzes React Native codebases to map feature implementations across screens, components, state management, navigation, and API layers. Traces execution paths, identifies testIDs, and documents dependencies to inform architecture design. Triggers: "explore the codebase", "how does this feature work", "map the…