Borrowing it
Nothing to install: this file belongs to lkmeta/txtify. 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/lkmeta/txtify/main/.claude/skills/verify/SKILL.mdgit clone --depth 1 https://github.com/lkmeta/txtifyWrote 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/lkmeta/txtify/verify)<a href="https://agentmods.dev/skills/lkmeta/txtify/verify"><img src="https://agentmods.dev/badge/skills/lkmeta/txtify/verify/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/lkmeta/txtify/verify"><img src="https://agentmods.dev/badge/skills/lkmeta/txtify/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 41 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
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 | $0.00054 | $0.00600 |
| Opus 5.5 | $0.00022 | $0.00240 |
| Sonnet 5.5 | $0.00011 | $0.00120 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
verify 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.
- The E2E script's container is removed on exit; to debug interactively, `docker run -d --rm --name txtify_dbg -p 8078:8011 txtify:e2e` and drive it with curl. How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verifying Txtify changes
Two tiers. Pick the cheapest one that actually exercises the change.
Tier 1 — unit/API tests (seconds, no ML stack needed)
pytest -q
Covers: format converters (incl. PDF Unicode round-trip), filename/URL/upload validation, job-id DB flow, /health, /transcribe error paths, DeepL alignment edge cases. tests/conftest.py stubs torch/stable_whisper when absent, so a light venv is enough:
grep -v -E '^(torch|stable-ts)' requirements.txt > /tmp/reqs.txt
pip install -r /tmp/reqs.txt pytest httpx pypdf
Sufficient on its own only for changes fully covered by tests (converters, validation, endpoint logic).
Tier 2 — Docker E2E (the real gate, ~5–10 min)
./scripts/docker_e2e.sh
Builds the image, boots a container, checks /health + all pages + 404s, uploads a generated clip, runs a real whisper-tiny transcription to 100%, validates preview in all four formats, downloads the zip and confirms the PDF is in it, and checks validation errors. Success is the literal line PASS: docker E2E complete.
Mandatory for changes to: requirements.txt, Dockerfile, .dockerignore, src/transcribe_process.py, src/models.py, the worker-spawn path in src/utils.py.
Reading failures
- Status stuck at 10% → worker crashed at import (classic cause: an incompatible torch/torchaudio pair). Reproduce inside the container:
docker exec <name> python /app/src/transcribe_process.py 99 output/<clip> en whisper_tiny none en all - Status stuck at 30% for a long time → model download in progress; not a failure yet.
- Job errors mid-run →
docker exec <name> cat output/<job id>_logs.txt(the server log won't show worker errors). - The E2E script's container is removed on exit; to debug interactively,
docker run -d --rm --name txtify_dbg -p 8078:8011 txtify:e2eand drive it with curl.
What "verified" means in a PR body
Paste the actual output: the pytest summary line and/or the PASS: docker E2E complete line. A claim without output doesn't count.
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 cf4a2bdb0d06
- 1mo ago First seen · 46 lines · 54 tokens per session scan A 5f882476dcae
verify is a skill published in the GitHub repository lkmeta/txtify (135 stars, last pushed today), licensed Apache-2.0. It adds 54 tokens to every session and 600 once invoked, about $0.0002 per session on Opus 5.5. 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
pytest-suite
Write or extend the backend test suite following this project's conventions. Use when adding tests for a new service/route/repository, when coverage is missing, or when asked to test a feature. Knows the mocked-session + httpx AsyncClient setup so tests run with no database.
python-testing
Write or modify Python tests. Use when: adding new tests, understanding testing conventions, working with fixtures, writing FastAPI route tests, database tests, or following pytest patterns. DO NOT USE FOR RUNNING TESTS. If you are just running tests, not building them, you do not need this.
background-task
Add or modify work that runs outside the request/response cycle — emails, document ingestion, webhooks, cleanups, scheduled jobs. Use when something is slow or fire-and-forget, or when adding a periodic/cron task. This project's queue is {{ cookiecutter.backgroundtasks }}.
agent-tool
Add a new tool/function the AI agent can call (e.g. look something up, hit an external API, perform an action). Use when extending the assistant's capabilities, wiring a new function into the agent, or when the model needs a new action. This project uses {{ cookiecutter.aiframework }}.
frontend-feature
Build a new page, view, or data-driven feature in the Next.js frontend. Use when adding a route under the dashboard/marketing area, wiring UI to a backend endpoint, adding client state, or creating a localized page. Covers App Router, data fetching, Zustand stores, and i18n.
rag-knowledge
Work with the RAG knowledge base — ingest documents, run semantic search, manage collections, or add a sync source/connector (Google Drive, S3). Use when populating or debugging the knowledge base, tuning retrieval, or adding a new document source. This project uses {{ cookiecutter.vectorstore }} + {{…