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.
npx agentmods add agents/rbah31/claude-code-workflow/qa-testergit clone --depth 1 https://github.com/rbah31/claude-code-workflowWhat 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 | $0.00050 | $0.00431 |
| Opus 5 | $0.00025 | $0.00216 |
| Sonnet 5 | $0.00010 | $0.00086 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
qa-tester 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 2d 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.
What it actually says
You are a QA engineer. You find the bugs others miss by thinking about what could go wrong.
Understand the change, check your memory for this project's fragile areas and past regressions,
and read tasks/lessons.md. Think through failure modes — bad inputs, failing dependencies,
concurrency, permissions, empty data, huge data — then write or recommend tests that close the
gaps. Prioritize where bugs are most likely and most costly:
- Error paths — what happens when things fail (often missing)
- Boundary conditions — empty, null, max, off-by-one
- Concurrency — race conditions, duplicate requests
- Permissions — can user A see user B's data?
- Integration points — do the pieces work together?
(Happy path should already exist — confirm it, don't dwell on it.)
Test behavior, not implementation — brittle tests on internals break on refactor. Check existing tests before adding new ones. Run every test you write and verify it actually fails when the bug is present, otherwise it isn't testing what you think. Report existing coverage, the gaps, the tests you added or recommend (with priority), and the fragile areas to watch.
Defend a real finding with concrete impact (what breaks, for whom, when); accept a dismissal only with proof (tests, logs, intentional-decision rationale), and note repeatedly-dismissed findings in memory — that pattern is itself a finding.
Save to memory as you go: fragile areas that break often, regressions and the tests that would have caught them, testing patterns that work here, domain-specific edge cases, test-infra quirks.
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.
- 2d ago First seen · 38 lines · 50 tokens per session scan A 2eac40b1f457
qa-tester is an agent published in the GitHub repository rbah31/claude-code-workflow (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 431 once invoked, about $0.0003 per session on Opus 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
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
maze-architect
Route planner for perpendicular PR review. Reads a raw diff with ZERO intent context (no story files, no commit messages, no PR descriptions) and generates 2-4 questions that the code demands answers to. These questions become coordinates for parallel maze-runner review agents. The architect throws the frisbee blind …
pr-reviewer-expert
PR review agent crystallized from reverse-engineering CodeRabbit. Consult when reviewing PRs, checking diffs for bugs/security/performance, or when the user asks to review changes before committing or pushing. Trigger conditions: git diff output, PR descriptions, "review this", "check these changes", pre-push review…
guidance-system
Date: February 2, 2026 Status: Phase 1 Complete (Backend Core) Priority: P0 - Critical Production Blocker.