Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Superstack Deps

ASecurity

Dependencies need moving — an EOL or deprecation notice, a security advisory, "upgrade to vX", "how far behind are we". Also on "upgrade dependencies". Skip for new dependencies (superstack-decide), lockfile-only patch bumps, and updating the superstack plugin itself (the plugin manager's job).

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentssecurity

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add debabsah/superstack --skill superstack-deps --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Superstack Deps?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Superstack Deps
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/debabsah-superstack-deps/badge)](https://www.skillsdirectory.com/skills/debabsah-superstack-deps)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: superstack-deps
description: Dependencies need moving — an EOL or deprecation notice, a security advisory, "upgrade to vX", "how far behind are we". Also on "upgrade dependencies". Skip for new dependencies (superstack-decide), lockfile-only patch bumps, and updating the superstack plugin itself (the plugin manager's job).
---

# superstack-deps

The platform moves under every project. An upgrade is ordinary work with one distinguishing risk: the breaking change you didn't read about — so the method is inventory, batches, and a checkpoint per batch.

## The method

1. **See green first, then inventory — printed.** Run the project's named verify command *before* any bump: a post-bump red you can't attribute is two hours of bisecting a failure that predated you (scope's rule, applied here). Then the inventory: what's depended on, current vs latest, EOL/advisory flags, and which dependencies are load-bearing vs incidental. When the work spans sessions, the inventory lives at the top of the task file (`.superstack/tasks/<slug>.md`) — dated, so the next session diffs against it instead of re-deriving it.
2. **Batch by risk, not alphabet.** Patch-safe bumps travel together; each major travels **alone**, with its breaking-change digest read from the actual changelog — opened, not guessed (R1: the changelog is a file you haven't opened yet).
3. **Each batch ends at a checkpoint:** the project's named verify command green, then a commit — so any batch is a legal stopping point and execution moves verified-state to verified-state (the plan shape). Rollback per batch is the commit revert — which stays true only if batches are pure: **no drive-by refactors inside an upgrade commit.**
4. **A big migration is a campaign.** Framework major, runtime jump, anything spanning sessions: open a plan file and run superstack-execute — this skill is its inventory-and-batching front end, not a substitute for the campaign loop.
5. **A pin is a decision.** What stays behind, stays behind *with its reason recorded* (a superstack-decide record or the overlay's Conventions, with a revisit trigger) — pinned-with-reason ages into a plan; silently stale ages into an incident.

## The ledger

What moved (versions, before → after), what the verify command showed per batch, and what remains behind with its why. `Assumed:` covers the transitive surface honestly — a green suite proves what the suite covers, not the dependency tree's whole behavior.

Attribution

debabsahdebabsah
View sourceMore from debabsah →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →