A project-local setup and inspection workflow for quality-assurance information, such as the project stack, test settings, environments, and authorization limits. It creates only missing context and does not run tests or install tools.

Use it to initialize or inspect QA context, record requested tool probes, and document available browsers, devices, CI, data restrictions, and testing boundaries.

It gives later QA work a reliable view of the project without overwriting existing information or reading outside the project root.

qa-init — Skill for Claude Code by pwdev-solucoes

Install

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.

Any agent

npx skills add pwdev-solucoes/pwdev-claude-marketplace --skill qa-init

Clone the repo

git clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplace

Made for: Claude Code.

Or install pwdev-qa, the plugin that ships this one along with the rest of its 16 skills, 6 commands.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/qa-init/github.svg)](https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/qa-init)

Your own site

<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/qa-init"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/qa-init/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/qa-init"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/qa-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,305 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00021	$0.01305
Opus 5.5	$0.00008	$0.00522
Sonnet 5.5	$0.00004	$0.00261
Haiku 4.5	$0.00002	$0.00130

Measured 1mo ago against content hash 3956c988ff90, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

qa-init 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.

plugins/pwdev-qa/skills/qa-init/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Initialize PWDEV QA context

Observe the selected project, preserve its contracts and approvals, and create only missing QA context inside the project root. This workflow inventories capabilities; it does not execute tests. Read workflow, safety, artifacts, and tooling first.

Inputs

The explicit project root, target, objective, and identified contract.
The complete supplied criterion catalog with its original IDs and exact text, or an explicit statement that it is missing.
Existing .planning/pwdev-qa/context.md, project stack, test configuration, CI information, environments, devices, browsers, data restrictions, budget, and authorization boundaries.
A requested probe inventory. Each probe records state (positive, negative, or not_run), the exact check, its result, and observed evidence.

Procedure

Resolve and identify the project root. Confine every inspection and context write within that project root; do not scan parent directories, user configuration, secrets, or personal browser state.
Inspect .planning/pwdev-qa/context.md without following symlinks. Refuse a symlink or a non-regular existing path. Preserve and never overwrite an existing context file. If it is absent, create its parent directories and the context file only inside the project, using an exclusive create so a concurrent or newly appearing file is preserved.
Preserve the explicit objective and authorization boundaries exactly. Record only observed project facts: target, contract identity, criterion IDs and text, surfaces, stack, existing test entry points, CI, environments, data restrictions, approvals, and unknowns. Do not infer approval, a complete catalog, or an installed tool.
Run only safe, read-only probes that the user or project context permits. Record a skipped probe as not_run. A probe result is observation, not authorization to run tests or contact an external service.
Consult qa-tooling with the observed stack, surface, runtime/OS, CI, budget, restrictions, authorization, and the exact probe inventory. Preserve probe states positive, negative, and not_run and its table without reclassifying absent probes.
Classify tools exactly as available, missing, or unverified: only an explicit negative tool probe means missing; an absent/not-run probe or unmet prerequisite means unverified. Never install, configure, or claim execution of a tool.
Apply the shared verdict rules to the current QA state. Missing criteria, unsafe evidence, or pending required capability is BLOCKED; a proven current in-scope failure is FAIL and prevails. Initialization alone never supplies a PASS result.

Read the full file on GitHub · 106 lines

Changes

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 · 106 lines · 21 tokens per session scan A 3956c988ff90

Subscribe to this mod's changes

qa-init 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 21 tokens to every session and 1,305 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.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

qa-init