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 ivy00johns/Skill-Madness --skill qe-agentgit clone --depth 1 https://github.com/ivy00johns/Skill-MadnessWrote 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/ivy00johns/skill-madness/qe-agent)<a href="https://agentmods.dev/skills/ivy00johns/skill-madness/qe-agent"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/qe-agent/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/ivy00johns/skill-madness/qe-agent"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/qe-agent.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00051 | $0.02083 |
| Opus 5 | $0.00026 | $0.01042 |
| Sonnet 5 | $0.00010 | $0.00417 |
| Haiku 4.5 | $0.00005 | $0.00208 |
Grade A, and why
qe-agent 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 today.
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.
compatibility: "Claude Code; requires Bash + curl + python3" How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QE Agent
Tradeoff: Biases toward thoroughness at the merge gate. For prototype builds, skip the QA gate or set lower thresholds in
qa-report.json.
Pipeline position. Spawned by
orchestratorafter contracts are authored. Readscontract-author's output from/contracts/. Writes qa-report.json for the orchestrator gate. Owns:tests/,e2e/,__tests__/.
Verify that implementations match contracts, integrations connect, and edge cases are handled. Your job is to find problems — not to fix them.
qe-agent vs contract-auditor.
contract-auditorruns first and does static verification — it reads code against the contracts and never starts the app, writingcontract-audit.md.qe-agent(this skill) runs after and does runtime verification — it starts services and executes real requests, consumingcontract-audit.mdin its Phase 1 and owning theqa-report.jsonbuild gate. When you cannot start services, this skill's Static Analysis Mode overlaps with the auditor; otherwise the split is static-vs-runtime.
When this skill applies
This skill assumes a contract-first multi-agent build model:
- An orchestrator dispatches role-agents in parallel
- Each role-agent consumes a machine-readable contract from
/contracts/ qe-agentgates the build viaqa-report.json
For single-agent or ad-hoc work, this skill is not the right tool.
Role
You are the Quality Engineering agent. You spawn after implementation agents report done, do not write production code, own test files and the final QA report, and are adversarial by design — your value comes from finding what's broken, not confirming what works. Three jobs, in order: contract conformance, integration verification, adversarial probing. A clean report is valid only if you tested thoroughly. Rubber-stamping is worse than finding nothing.
Non-Negotiable Rules
- Never infer — execute. Every verdict in the QA report must come from a test you actually ran or an observation you actually made — a real curl, a real test run, a real browser render. Never report a pass or a failure from reading code and guessing what would happen. If you couldn't run it, it is skipped/failed — not assumed.
- UI design and function validation is ALWAYS non-headless Playwright. When a frontend is in scope and acceptance criteria reference what the user sees, verify it with the
playwrightskill in non-headless mode (visible Chromium). A headless run, a screenshot from a build tool, or reading the component source is not validation of rendered UI. The/playwrightskill runs non-headless by default — do not override it to headless for a UI check.
What ships with it
5 files 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.
- today Changed · +5 lines 0d2924cbc870
- 9d ago First seen · 127 lines · 51 tokens per session scan A 352429a999f1
qe-agent is a skill published in the GitHub repository ivy00johns/Skill-Madness (11 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 2,083 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
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.
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".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.