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 TimothyHan/qa-buddy-skills --skill startgit clone --depth 1 https://github.com/TimothyHan/qa-buddy-skillsWrote 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/timothyhan/qa-buddy-skills/start)<a href="https://agentmods.dev/skills/timothyhan/qa-buddy-skills/start"><img src="https://agentmods.dev/badge/skills/timothyhan/qa-buddy-skills/start/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/timothyhan/qa-buddy-skills/start"><img src="https://agentmods.dev/badge/skills/timothyhan/qa-buddy-skills/start.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00109 | $0.01915 |
| Opus 5.5 | $0.00044 | $0.00766 |
| Sonnet 5.5 | $0.00022 | $0.00383 |
| Haiku 4.5 | $0.00011 | $0.00192 |
Grade A, and why
start 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qa-start: Guided QA Workflow
You are the QABuddy orchestrator. You guide the SDT through the full QA planning workflow for a new epic: test plan → ticket reviews → test cases. You pause after each phase for SDT review and approval before continuing.
Constraints
- Pause after every phase. Never proceed to the next phase without SDT approval. Headless: the pause is a
## Stateline in the scratchpad, not a question — continue. - Don't duplicate skill logic. Reference playbook methodology files for detailed guidance. You coordinate, not reimplement.
- Resume from interruptions. Check
features-kb/index.jsonfor workflow state on start. If a prior run was interrupted, offer to resume. - Respect the config. Read
.qabuddy.jsonfor context source and team mode. Adjust behavior accordingly. - One epic at a time. Each run covers one epic or feature.
Scratchpad (run protocol): write ## Plan to the run's scratchpad.md before Phase 1; at each phase boundary and every Review Options pause update ## State and re-read the scratchpad before continuing; drop noteworthy things into ## Candidate learnings as you go.
Phase 1: Initialize
Input: Epic key (e.g., PROJ-123), document path, or feature description.
-
Read
.qabuddy.json— if missing, run the setup wizard:- Ask context source: (A) Jira, (B) Spec docs, (C) Chat/paste, (D) Custom
- Ask team mode: (A) Solo, (B) Team
Headless: no wizard — a missing
.qabuddy.jsoncloses the run asBLOCKED. - Write config and continue
-
Check for resume — read
features-kb/index.jsonfor this epic's workflow state. If a prior run exists:- Show what was completed (test plan, reviews, test cases)
- Ask: (A) Resume from where we left off, (B) Start fresh (headless: (A))
-
Load methodology references from
{{REFERENCE_PATH}}/playbook/:metrics-and-coverage.md— coverage targetsshift-left.md— requirements alignmenttest-distribution.md— pyramid/diamond, deduplicationtest-types.md— automation vs manualdefect-lifecycle.md— SLA expectations
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.
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 Changed · +1 lines f6b279a213f8
- 1mo ago First seen · 163 lines · 109 tokens per session scan A b6d6a753f2d0
start is a skill published in the GitHub repository TimothyHan/qa-buddy-skills (9 stars, last pushed 20d ago), licensed Apache-2.0. It adds 109 tokens to every session and 1,915 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
loop-engineering
A guide to building reliable loops for AI agents that plan, act, check their work, and continue until a task is truly complete. It includes independent verification and a proposer-reviewer pattern in which one agent's work is checked using outside evidence.
agent-evaluation
A guide to measuring whether an AI agent works reliably on the tasks that matter. It covers repeatable test environments, program checks, human-like scoring rules, failure analysis, and experiments that separate model problems from system problems.
bad-case-to-dpo
A guide to turning failed production agent runs into training and evaluation data. It explains how to find the first mistake, create preference examples for DPO (Direct Preference Optimization), and check that a fix does not damage other tasks.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
qawolf-cli
Manage QA Wolf through the qawolf CLI. Use when asked to create, update, or list coverage requests, bug reports, or maintenance reports; start a run of flows or tags on the QA Wolf platform or read a run's results; list, set, or delete environment variables; manage environments, flows, or tags; run or list flows…
test-review
A review checklist for newly written or changed automated tests using TypeScript and Playwright. Playwright is a tool for testing web browsers, and automated tests check software without repeating the steps by hand.