txtify: Skill for Claude Code

.claude/skills/deps-bump/SKILL.md

deps-bump is a skill for Claude Code from lkmeta/txtify. It costs 35 tokens per session (600 once invoked), scanned A, original, Apache-2.0.

A workflow for safely updating Txtify's software dependencies and resolving Dependabot security alerts. Dependencies are outside packages that the application relies on.

In plain words
What is it for?
It helps bump packages, remove unused dependencies, keep related Torch packages aligned, check Whisper compatibility, and test YouTube downloads after updating yt-dlp.
Why use it?
It helps avoid version mismatches, broken builds, and silent download failures while changing packages. It also checks whether a dependency is actually used before updating it.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is lkmeta/txtify's own configuration. It tells Claude Code how to work on txtify itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything txtify configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/lkmeta/txtify/main/.claude/skills/deps-bump/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lkmeta/txtify

Made for: Claude Code.

Wrote 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.

agentmods badge for deps-bump

README.md
[![agentmods](https://agentmods.dev/badge/skills/lkmeta/txtify/deps-bump.svg)](https://agentmods.dev/skills/lkmeta/txtify/deps-bump)
Your own site
<a href="https://agentmods.dev/skills/lkmeta/txtify/deps-bump"><img src="https://agentmods.dev/badge/skills/lkmeta/txtify/deps-bump.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 600 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.00600
Opus 5 $0.00017 $0.00300
Sonnet 5 $0.00007 $0.00120
Haiku 4.5 $0.00003 $0.00060

Measured 8d ago against content hash 8ecace0a8c97, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

deps-bump 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 8d 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.

.claude/skills/deps-bump/SKILL.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dependency updates for Txtify

Ground rules

  1. torch and torchaudio move together, same version. A mismatch doesn't fail the build — it crashes the worker at import, and jobs just hang at 10%. This is the #1 trap.
  2. stable-ts ≥ 2.19.1 so pip resolves an openai-whisper that builds under modern setuptools (older ones import pkg_resources in setup.py and break the Docker build). Check stable-ts's openai-whisper constraint before bumping torch far ahead.
  3. Before adding any package, and before "fixing" an alert on one: check it's actually imported — grep -rn '<pkg>' src/. Unused packages get deleted, not bumped (transformers/accelerate/srt/webvtt-py died this way).
  4. yt-dlp rots fastest and breaks YouTube downloads silently. After bumping, verify with a real download (host venv is fine):
    import yt_dlp
    opts = {"format": "bestaudio/best", "postprocessors": [{"key": "FFmpegExtractAudio", "preferredcodec": "mp3", "preferredquality": "192"}], "outtmpl": "yt_test.%(ext)s", "quiet": True}
    yt_dlp.YoutubeDL(opts).download(["https://www.youtube.com/watch?v=jNQXAC9IVRw"])  # 19s clip
    
  5. Runtime deps go in requirements.txt; test-only deps (pytest, httpx, pypdf) in requirements-dev.txt. Don't ship test tooling in the image.

Checking alerts

gh api repos/lkmeta/txtify/dependabot/alerts --paginate \
  --jq '.[] | select(.state=="open") | [.security_advisory.severity, .dependency.package.name, .security_vulnerability.vulnerable_version_range, (.security_vulnerability.first_patched_version.identifier // "none")] | @tsv'

Pick the newest version that is explicitly patched in the alert set rather than blindly taking latest — conservative for the ML stack, current for everything else. Alerts auto-resolve after GitHub rescans the updated manifest (minutes to hours); don't chase the counter.

Verification (non-negotiable)

Any requirements.txt change requires the full Docker E2E — the unit tests stub the ML stack and will pass even when the worker can't import: run the verify skill, Tier 2 (./scripts/docker_e2e.shPASS: docker E2E complete).

Read the full file on GitHub · 33 lines

Changes

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.

  1. 8d ago First seen · 33 lines · 35 tokens per session scan A 8ecace0a8c97

Subscribe to this mod's changes

deps-bump is a skill published in the GitHub repository lkmeta/txtify (135 stars, last pushed 23d ago), licensed Apache-2.0. It adds 35 tokens to every session and 600 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 2026-08-30.

Related

Other skills, from other repositories

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 }}.

vstorm-co/full-stack-ai-agent-template · 62 tokens

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 }}.

vstorm-co/full-stack-ai-agent-template · 66 tokens

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.

vstorm-co/full-stack-ai-agent-template · 64 tokens

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 }} + {{…

vstorm-co/full-stack-ai-agent-template · 76 tokens

alembic-migration

Create, review, and apply database schema changes with Alembic. Use whenever a SQLAlchemy model is added or changed, a column/index/constraint needs to change, or a data backfill is required — anything that alters the PostgreSQL schema.

vstorm-co/full-stack-ai-agent-template · 56 tokens

channel-bot

Work with messaging-channel bots (Telegram / Slack) — register a bot, route inbound messages through the AI agent, handle webhooks vs polling, or add a new channel adapter. Use when wiring chat into a messaging platform or debugging bot delivery.

vstorm-co/full-stack-ai-agent-template · 53 tokens