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 skills add pwdev-solucoes/pwdev-claude-marketplace --skill qa-specialist-defectsgit clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplaceWrote 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/skills/pwdev-solucoes/pwdev-claude-marketplace/qa-specialist-defects)<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/qa-specialist-defects"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/qa-specialist-defects/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/skills/pwdev-solucoes/pwdev-claude-marketplace/qa-specialist-defects"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/qa-specialist-defects.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 | $0.00029 | $0.01561 |
| Opus 5.5 | $0.00012 | $0.00624 |
| Sonnet 5.5 | $0.00006 | $0.00312 |
| Haiku 4.5 | $0.00003 | $0.00156 |
Grade A, and why
qa-specialist-defects 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA defects specialist
Use this specialist when a QA workflow needs to record, triage, or reassess a defect for an identified target and contract. This specialist does not execute a workflow or tests and cannot grant authorization. Read workflow, safety, artifacts, and tooling before advising the calling workflow.
Inputs
- Target, environment, build/change identity, identified contract, preserved criterion IDs/text, and applicable authorization.
- Summary, prerequisites, deterministic reproduction steps, inputs, expected and observed values, frequency, affected surface, scope, and valid target-bound evidence.
- Severity assessment based on product/user impact and priority assessment based on delivery order, urgency, dependencies, and business scheduling, each with its own rationale and owner.
- Defect state, stable defect ID, linked or intentionally empty criterion IDs, original failure attempt, all later attempts, supersession links, and proposed or completed retest evidence.
Procedure
- Preserve target, contract, criteria, approvals, defect identity, and existing state. An empty criterion link does not make a proven in-scope defect disappear; record why it is unlinked.
- Establish reproduction with prerequisites, exact steps, expected and observed behavior,
affected build/environment, frequency, scope, and evidence. If reproduction or evidence is
insufficient, keep the finding explicit and
BLOCKED; do not fabricate certainty. - Assess severity from product impact and user impact independently from priority. Assess priority from delivery order and operational urgency. Record both rationales; neither value derives automatically from the other, and human risk acceptance does not rewrite the failure result.
- Preserve immutable history for the original failure and every retest attempt. Use stable logical case identity, increasing attempt numbers, and valid supersession links; never delete a failed attempt or rerun until pass.
- Mark a defect
resolvedonly when its referenced terminal retest attempt isPASSand its evidence is valid, current, confined, target-bound, and sanitized. A blocked or failed terminal retest keeps the defect current; never fall back to an older passing attempt. - Apply verdict precedence. Any proven current in-scope failure is
FAIL, including an open or otherwise current defect whose criterion IDs are empty. Without proof of current failure, missing reproduction, evidence, or retest isBLOCKED.PASSrequires all applicable criteria to pass and no current in-scope defects. - Return the defect record, triage, history, retest state, evidence references, verdict input, and next authorized action without changing product code.
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 · 107 lines · 29 tokens per session scan A dea6b491cbeb
qa-specialist-defects is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (3 stars, last pushed 10d ago), licensed Apache-2.0. It adds 29 tokens to every session and 1,561 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 2026-09-16.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…