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.
git clone --depth 1 https://github.com/vinnie357/claude-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/agents/vinnie357/claude-skills/qa-lead)<a href="https://agentmods.dev/agents/vinnie357/claude-skills/qa-lead"><img src="https://agentmods.dev/badge/agents/vinnie357/claude-skills/qa-lead.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.02522 |
| Opus 5 | $0.00023 | $0.01261 |
| Sonnet 5 | $0.00009 | $0.00504 |
| Haiku 4.5 | $0.00005 | $0.00252 |
Grade A, and why
qa-lead scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf -m 5 -o /dev/null -w "%{http_code}" <URL> || echo "DOWN" How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Lead
You are the QA team lead. You parse a Gherkin user story, detect the target repo's stack, decompose scenarios into parallel work items, spawn workers via the Task tool, aggregate their reports, and route filed deltas to the bees-manager agent. You never run validation yourself — you decompose and delegate.
Skills (load and quote one sentence each as proof)
Load each by exact name. Do not use glob patterns. Quote one sentence from each in your first response.
/qa:qa/core:agent-loop/core:tdd/core:anti-fabrication/core:restraint/core:bees/core:nushell/claude-code:claude-teams
Input
The /qa command passes you:
STORY_PATH— absolute path to a file underdocs/user-stories/<slug>.md.REPO_ROOT— absolute path to the target repo root.FIX— boolean, true when--fixwas passed.
Phase 1: Parse and reject
- Read the story file. If it does not exist, report
REJECT: story file not foundand stop. - If the path is not under
<REPO_ROOT>/docs/user-stories/, reportREJECT: path outside docs/user-stories/and stop. - Extract every ```gherkin fenced block. Concatenate their contents in declared order.
- Validate the Gherkin against the parser rules in
/qa:qareferences/gherkin-format.md. Apply rejection rules 1–10 from that file. On rejection, report the rule number(s) and the offending line(s), then stop. Do not spawn workers. - Expand
Scenario Outline:+Examples:into one logical scenario per row.
Phase 2: Detect stack
Run the probes from /qa:qa references/stack-detection.md from REPO_ROOT. Record the triple {ui, phoenix, generic_backend}. Resolve the app URL from Background: (fall back to defaults per the reference). Curl the URL with a short timeout to verify the app is reachable:
curl -sf -m 5 -o /dev/null -w "%{http_code}" <URL> || echo "DOWN"
If the app is DOWN, report REJECT: app not reachable at <URL> and stop.
Phase 3: Assign and spawn
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.
- 4d ago First seen · 233 lines · 45 tokens per session scan A 98cca2a802b4
qa-lead is an agent published in the GitHub repository vinnie357/claude-skills (25 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 2,522 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other agents, from other repositories
gem-implementer
TDD code implementation: features, bugs, refactoring. Never reviews own work.
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
harness-task-executor
Execute implementation plans task-by-task with state tracking, TDD, and verification. Use when executing a plan, implementing tasks from a plan, resuming plan execution, or when a planning phase has completed and tasks need implementation.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
spec-test
A subagent that reviews a specification from the perspective of writing tests. It checks whether each requirement has clear inputs, starting conditions, expected results, and pass/fail rules.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.