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 makifbaysal/tasktrooper --skill accessibility-checkgit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/accessibility-check)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/accessibility-check"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/accessibility-check/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/makifbaysal/tasktrooper/accessibility-check"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/accessibility-check.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 | $0.00040 | $0.01164 |
| Opus 5.5 | $0.00016 | $0.00466 |
| Sonnet 5.5 | $0.00008 | $0.00233 |
| Haiku 4.5 | $0.00004 | $0.00116 |
Grade A, and why
accessibility-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Check
Thresholds
The same bar the frontend developer builds to (accessibility-basics, ui-quality-floor, responsive-mobile-first) — QA and developer share one bar, not a separate QA opinion:
- labels on every control,
aria-labelon icon-only buttons; - visible focus on every interactive element;
- contrast ≥4.5:1 body text / ≥3:1 large text;
- touch targets ≥44px phone / ≥24px desktop;
<input>font ≥16px on phone;- exactly one
<h1>,langset on<html>, nouser-scalable=no; - a dialog traps focus while open,
Escapecloses it, focus returns to the trigger; - submitting with errors moves focus to the first invalid field, which carries
aria-invalid.
Scan (public pages)
QA=${TMPDIR:-/tmp}/tt-<task-key>/qa; mkdir -p "$QA"; node -v # lighthouse@13 needs Node >=22, else lighthouse@12
CHROME_PATH="$CHROME_BIN" npx -y lighthouse@13 "http://localhost:5173/settings" \
--only-categories=accessibility,best-practices --form-factor=mobile \
--screenEmulation.mobile --screenEmulation.width=360 --screenEmulation.height=800 --screenEmulation.deviceScaleFactor=2 \
--chrome-flags="--headless=new" --output=json --output-path="$QA/lh-settings-360.json" --quiet
jq -r '.audits|to_entries[]|select(.value.score==0)|"\(.key)\t\(.value.title)"' "$QA/lh-settings-360.json" # no jq: node -e 'for (const [k,v] of Object.entries(require(process.argv[1]).audits)) if (v.score===0) console.log(k+"\t"+v.title)' "$QA/lh-settings-360.json"
Run with run_terminal timeout_seconds: 300. errors-in-console in the output doubles as the console check for page load.
Full axe (pages behind login, or when Lighthouse flags something)
Install playwright-core + @axe-core/playwright into $QA, never the workspace:
cd "$QA" && [ -d node_modules/@axe-core/playwright ] || npm i --no-audit --no-fund --silent [email protected] @axe-core/[email protected]
cat > axe.cjs <<'EOF'
const { chromium } = require('playwright-core');
const { AxeBuilder } = require('@axe-core/playwright');
(async () => {
const [url, width = '360'] = process.argv.slice(2);
const browser = await chromium.launch({ executablePath: process.env.CHROME_BIN });
const page = await browser.newPage({ viewport: { width: Number(width), height: 800 } });
await page.goto(url);
const { violations } = await new AxeBuilder({ page })
.withTags(['wcag2a', 'wcag2aa', 'wcag21a', 'wcag21aa', 'wcag22aa']).analyze();
for (const v of violations) console.log(`${v.impact}\t${v.id}\t${v.nodes.length}\t${v.nodes[0].target.join(' ')}`);
console.log(`violations=${violations.length}`);
await browser.close();
})();
EOF
node axe.cjs http://localhost:5173/settings 360
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.
- 6d ago Changed 01d945761345
- 8d ago First seen · 83 lines · 40 tokens per session scan A 972b6e0cdd6d
accessibility-check is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 40 tokens to every session and 1,164 once invoked, about $0.0002 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 2026-10-05.
Other skills, from other repositories
qa-acceptance
Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states, performance limits, and explicit pass/fail evidence.
nemo-automodel-model-onboarding
Guide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation patterns, registration, and validation.
amc-run-sample-calibration
Run end-to-end calibration on the shipped sample dataset (sdg082sampledata010926.zip) against a running AMC microservice. Use when user says 'test sample dataset', 'run sample calibration', 'verify AMC install', or 'launch and test'.
nemo-automodel-recipe-development
Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.
mcore-testing
Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.
i4h-catheter-navigation-e2e
End-to-end smoke for catheter navigation covering setup, digital twin, DRR, and unit tests. Use when asked to run the full catheter workflow smoke or demo the v0.7 pipeline.