What is qa-author-by-task?

A procedure for a QA author to write task-specific test cases after a task lead assigns a master-plan task. QA means quality assurance: checking that software works as intended.

Use it to create structural, API, end-to-end, and functional tests under the project's task-based test-case folders, and to coordinate visual test specifications for interface work.

It prevents incomplete or premature test plans by checking required design, requirements, and API information first.

qa-author-by-task — Skill for Claude Code and Codex by evolplus: A procedure for a QA author to write task-specific…

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.

agentmods

npx agentmods add skills/evolplus/talos/qa-author-by-task

Any agent

npx skills add evolplus/talos --skill qa-author-by-task

Clone the repo

git clone --depth 1 https://github.com/evolplus/talos

Made for: Claude Code, Codex.

Or install talos, the plugin that ships this one along with the rest of its 55 skills, 2 commands, 4 hooks.

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/evolplus/talos/qa-author-by-task.svg)](https://agentmods.dev/skills/evolplus/talos/qa-author-by-task)

Your own site

<a href="https://agentmods.dev/skills/evolplus/talos/qa-author-by-task"><img src="https://agentmods.dev/badge/skills/evolplus/talos/qa-author-by-task.svg" alt="Measured on agentmods" height="20"></a>

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 611 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00071	$0.00611
Opus 5	$0.00036	$0.00305
Sonnet 5	$0.00014	$0.00122
Haiku 4.5	$0.00007	$0.00061

Measured 3d ago against content hash 1fb31efb99b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-author-by-task 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 3d 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.

skills/qa-author-by-task/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Author By-Task

Use

Use this skill for QA-Author by-task mode. Load test-case-author for TC format, ui-test-execution for executable specs, and visual-spec-author before writing structural tests for UI tasks.

Inputs

Task file under docs/plan/phase-*/tasks/<task-id>.md
Linked US/FR files
docs/architecture.md
Frozen API contracts for BE/BE+FE tasks
docs/uiux/handoffs/<task-id>.md and docs/instrumentation-contract.md for UI tasks
Existing by-us test cases for linked US IDs

Preconditions

TL has linked US IDs and FR IDs.
UI tasks have design-confirmed and a handoff on main.
FE tasks dependent on BE contracts have frozen API contracts.
Missing preconditions cause NEEDS_CONTEXT/blocked return; do not author partial task TCs silently.

Procedure

Verify by-us coverage exists for each linked US. If missing, file an open issue and continue only for task-specific layers that can be authored safely.
Determine required task layers:
- api.md for BE or BE+FE contract/API work;
- structural.md for UI tasks;
- e2e.md for multi-system or cross-surface flows;
- functional.md only for task-specific behavior not covered by by-us.
For UI tasks, run visual-spec-author first. Structural TCs derive from docs/uiux/visual-specs/<task-id>.md, not from ad-hoc Figma interpretation.
For API tests, read both the FR file and frozen API contract. If they disagree, file an open issue; do not silently let one override the other.
Author markdown TCs under docs/test-cases/by-task/<task-id>/.
Author executable specs at every TC's Executable: path using the project runner conventions.
Ensure runner test names start with the TC ID.
Emit plan-update.json with track: "qa" and by-task notes.

Hard Rules

Never author by-task cases into by-us paths or the reverse.
Never invent missing API contract behavior.
Never write structural UI tests before visual spec exists.
Every executable TC needs a real spec file.
Commit before signaling ready-to-finalize.

Read the full file on GitHub · 54 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

agents/openai.yaml 231 B

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.

3d ago First seen · 54 lines · 71 tokens per session scan A 1fb31efb99b4

Subscribe to this mod's changes

qa-author-by-task is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 29d ago), licensed Apache-2.0. It adds 71 tokens to every session and 611 once invoked, about $0.0004 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.

Backend and APIs Frontend Testing

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens