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 skills/vthinkdeveloper/vthink-agent-toolkit/qa-guidenpx skills add vthinkdeveloper/vthink-agent-toolkit --skill qa-guidegit clone --depth 1 https://github.com/vthinkdeveloper/vthink-agent-toolkitWhat 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 | $0.00051 | $0.01183 |
| Opus 5 | $0.00026 | $0.00592 |
| Sonnet 5 | $0.00010 | $0.00237 |
| Haiku 4.5 | $0.00005 | $0.00118 |
Grade A, and why
qa-guide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Testing Guide Generator
You are generating a QA testing guide for PR #$ARGUMENTS.
PR Data (pre-fetched)
PR Metadata
!gh pr view $ARGUMENTS --json title,body,baseRefName,headRefName,additions,deletions,changedFiles,labels,files
Changed Files
!gh pr diff $ARGUMENTS --name-only
Full Diff
!gh pr diff $ARGUMENTS
Your Task
Analyze the PR data above, then research the codebase to understand the full context and impact of the changes. Produce a QA testing guide saved to docs/qa-guide-pr-$ARGUMENTS.md.
Step 1: Understand the Changes
Read through the diff and PR description to understand:
- What feature was added or what bug was fixed
- Which areas of the application are touched
- What the user-visible behavior change is
Step 2: Research the Codebase
For each changed file, research its context:
- Read the full current file to understand the complete component, not just the diff
- Find callers/consumers using Grep to search for class names, method names, component names, and import references — this reveals what other parts of the app depend on the changed code
- Find related test files to understand existing test coverage
- Check configuration files if the change introduces or uses new properties or settings
- For frontend changes, trace which pages/views use the changed components and how user interactions flow through them
Step 3: Generate the QA Guide
Write the guide to docs/qa-guide-pr-$ARGUMENTS.md using the template below.
Critical rules for the guide:
- The audience is a QA tester who knows the product broadly but is NOT familiar with this specific feature or fix
- Write ZERO code, file paths, class names, or technical implementation details
- Describe everything in terms of what the user sees and does in the application
- Test steps should be exact: "Click the X button in the top-right corner of the dashboard", not "Test the feature"
- Explain the feature/fix context so the tester understands WHY they are testing what they are testing
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.
- yesterday First seen · 134 lines · 51 tokens per session scan A 66470954abb1
qa-guide is a skill published in the GitHub repository vthinkdeveloper/vthink-agent-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 1,183 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…