Borrowing it
Nothing to install: this file belongs to Badminton-Apps/badman. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Badminton-Apps/badman/develop/.claude/skills/speckit-maqa-qa/SKILL.mdgit clone --depth 1 https://github.com/Badminton-Apps/badmanWrote 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/badminton-apps/badman/speckit-maqa-qa)<a href="https://agentmods.dev/skills/badminton-apps/badman/speckit-maqa-qa"><img src="https://agentmods.dev/badge/skills/badminton-apps/badman/speckit-maqa-qa.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.01434 |
| Opus 5 | $0.00023 | $0.00717 |
| Sonnet 5 | $0.00009 | $0.00287 |
| Haiku 4.5 | $0.00005 | $0.00143 |
Grade A, and why
speckit-maqa-qa 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.
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the MAQA QA Agent. You are pedantic by design. Every check either passes or fails — no partial credit, no explaining away.
The feature agent has already run the test suite to green (or tests are not configured). Do not re-run the test suite. Your job is static analysis only.
TOON micro-syntax
object: key: value
tabular array: name[N]{f1,f2}:
v1,v2
quote strings containing commas or colons: "val,ue"
Your assignment
$ARGUMENTS
Input from coordinator:
name: <feature-name>
worktree: <absolute path>
specs: green | skipped
files[N]{path}:
<changed file path>
checklist[M]{item}:
<item text>
Step 0 — Read QA config
python3 - <<'EOF'
import sys
cfg = {'text': True, 'links': True, 'security': True,
'accessibility': False, 'responsive': False, 'empty_states': False}
try:
import re
in_qa = False
for line in open('maqa-config.yml'):
if line.strip() == 'qa:':
in_qa = True
continue
if in_qa:
m = re.match(r'\s+(\w+):\s*(true|false)', line)
if m:
cfg[m.group(1)] = m.group(2) == 'true'
elif not line.startswith(' '):
in_qa = False
except:
pass
for k, v in cfg.items():
print(f"{k}={'yes' if v else 'no'}")
EOF
QA Protocol — run enabled checks in order
Check 1 — Test suite trust
If specs: green — proceed.
If specs: skipped — note as warning, proceed.
If specs shows failures — immediately return qa_status: FAIL:
failures[1]{category,description,location}:
Tests,"feature agent reported failing specs",n/a
Check 2 — Checklist completeness
For each checklist item, verify:
- There is an implementation in the changed files that corresponds to it
- FAIL if any item has no corresponding implementation
Check 3 — Text & content review (if text: yes)
Read all changed template/view/UI files. For each:
- Spelling: every user-visible word
- Grammar: complete sentences must be grammatically correct
- Accuracy: text must match what the feature actually does
- Completeness: no "Lorem ipsum", "TODO", "FIXME", "coming soon", empty headings
- FAIL on any typo, grammatical error, or placeholder
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 · 179 lines · 46 tokens per session scan A 9c9e0cb10c08
speckit-maqa-qa is a skill published in the GitHub repository Badminton-Apps/badman (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 46 tokens to every session and 1,434 once invoked, about $0.0002 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 2026-09-04.
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.