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 agentmods add skills/wtotded/agentic-resume-builder/run-appnpx skills add WtotdeD/agentic-resume-builder --skill run-appgit clone --depth 1 https://github.com/WtotdeD/agentic-resume-builderWrote 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/wtotded/agentic-resume-builder/run-app)<a href="https://agentmods.dev/skills/wtotded/agentic-resume-builder/run-app"><img src="https://agentmods.dev/badge/skills/wtotded/agentic-resume-builder/run-app.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 | $0.00049 | $0.00844 |
| Opus 5 | $0.00024 | $0.00422 |
| Sonnet 5 | $0.00010 | $0.00169 |
| Haiku 4.5 | $0.00005 | $0.00084 |
Grade A, and why
run-app scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
code=$(curl -s http://localhost:3111/render/$c -o /tmp/$c.html -w '%{http_code}') How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run the app
Launch the Next.js dev server, then drive it. A 200 from a render route proves almost nothing here — see step 2.
1. Launch
PORT=3111 pnpm dev -p 3111 > /tmp/dev.log 2>&1 &
sleep 10 && tail -3 /tmp/dev.log
PORT must match -p. The export route builds its own base URL from
process.env.PORT (src/app/api/export-pdf/route.ts) rather than from the
incoming request, so leaving it unset makes PDF export fetch localhost:3000 —
either nothing, or some other project's server.
Stop it with pkill -f 'ne[x]t dev'. The bracket is load-bearing: a plain
next dev pattern matches the invoking shell's own command line and kills it.
2. Drive the render routes
sections: in a config matches ## headings by exact string and fails
silently, so check the HTML body, not the status code:
for c in $(ls resumes/*.yaml | xargs -n1 basename | sed 's/.yaml//'); do
code=$(curl -s http://localhost:3111/render/$c -o /tmp/$c.html -w '%{http_code}')
echo "$c $code: $(grep -oE '<h2[^>]*>[^<]+' /tmp/$c.html | sed 's/.*>//' | paste -sd' ')"
done
grep -ilE 'non-existent ID|Failed to' /tmp/*.html # expand: errors surface as an error box
grep -o, not grep -c — the HTML is minified onto two lines, so a line count
reports "2 sections" for every config regardless of what rendered.
Note this lists only top-level sections. The per-entry ## headings
(Achievements, Architecture, …) render as <h4>; to check those, grep <h4
the same way or read a screenshot. Compare against the config's sections:
list — a section listed there but missing from the page is a heading string
mismatch, not a render failure.
3. Export a PDF
curl -s -D /tmp/hdr.txt -o /tmp/out.pdf -X POST http://localhost:3111/api/export-pdf \
-H 'Content-Type: application/json' -d '{"configName":"tech-lead"}'
file /tmp/out.pdf # expect: PDF document, 2-4 pages
Page count is the signal worth reading — a template or content change that pushes a resume from 3 pages to 5 is a regression nothing else catches.
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.
- 5d ago First seen · 78 lines · 49 tokens per session scan A 59ce87772041
run-app is a skill published in the GitHub repository WtotdeD/agentic-resume-builder (2 stars, last pushed 10d ago), licensed MIT. It adds 49 tokens to every session and 844 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 2026-08-31.
Other skills, from other repositories
verify
Build/launch/drive recipe for verifying apps/docs changes at runtime (demos, docs pages, llms.txt).
e2e-tests-studio
REQUIRED when modifying any file in packages/playground-ui or packages/playground. Triggers on: React component creation/modification/refactoring, UI changes, new playground features, bug fixes affecting studio UI. Generates Playwright E2E tests that validate PRODUCT BEHAVIOR, not just UI states.
mastra-smoke-test
Smoke test Mastra projects locally or deploy to staging/production. Tests Studio UI, agents, tools, workflows, traces, memory, and more. Supports both local development and cloud deployments.
smoke-test
Create a Mastra project using create-mastra and smoke test the studio in Chrome using Chrome MCP server.
nextjs-ssr
Tag server-side fetches with the x-test-rcrd-id session header so SSR is recorded under the correct Playwright test session. Lead with registerProxyFetch (patch global fetch in the root layout, any runtime) and registerProxyAxios (per-axios-instance interceptor); createHeadersWithRecordingId is the patch-free per-call…
proxy-setup
Set up test-proxy-recorder for any Playwright project. Covers the proxy CLI (test-proxy-recorder --port --dir), package.json scripts for the three-service architecture (UI app → proxy → backend API), playwright.config.ts webServer block pointing to /control, per-test fixtures using playwrightProxy.before(page…