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/lkmeta/txtify/verifynpx skills add lkmeta/txtify --skill verifygit clone --depth 1 https://github.com/lkmeta/txtifyWhat 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 | $0.00054 | $0.00599 |
| Opus 5 | $0.00027 | $0.00300 |
| Sonnet 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 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.
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: torch/torchaudio version mismatch). 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.
- 3d 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 18d ago), licensed Apache-2.0. It adds 54 tokens to every session and 599 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
docker-compose
Work with the Docker Compose development environment. Use when: starting or stopping services, inspecting logs, opening a shell in a container, resetting the database, or understanding the service topology.
cortex-deploy
Cortex deployment — Docker Compose, envcheck.sh, CORTEX env vars, EC2/rsync, logs. Use for production setup, container config, or server debugging.
容器任务流程
容器任务的创建与管理流程指南，L1 创建/管理容器任务时加载。涵盖容器创建、workspace 决策、进度触发器、方案不可变原则、失败处理与工作空间规则、容器管理规则。.
docker-expert
Docker containerization, multi-stage builds, and optimization.
deep-research
深度研究编排方法论：澄清范围、拆解规划、并行调度子智能体调研、对抗式核验、综合成带引用的结构化报告。当任务需要多来源、可追溯、需事实核查的深度研究时使用此技能。.
mysql reporter
生成 MySQL 查询报表并生成可视化图表。当用户需要查询 MySQL 数据库并以报表形式展示结果时使用此技能，包括：统计销售数据、分析用户行为、生成业务报表、查询业务指标等。.