Last Pass — Security skill for Claude Code
Stage 4 last pass - fresh-eyes regression against ALL prior milestones (_firstinitial through _finalinitial), full gate-ladder re-run, and the format/dimension audit.
How to install Last Pass
Installs to ~/.claude/commands/remus3-legion-wallpaper-last-pass.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/Remus3/Legion-Wallpaper/HEAD/.claude/commands/last-pass.md -o ~/.claude/commands/remus3-legion-wallpaper-last-pass.md Restart Claude Code, or start a new session, for it to be picked up.
What Last Pass does
description: Stage 4 last pass - fresh-eyes regression against ALL prior milestones (_firstinitial through _finalinitial), full gate-ladder re-run, and the format/dimension audit. No new editing beyond reverts. Use when images sit in 7.Last Scratch or the operator says "last pass".
**SUBAGENT-FIRST (standing protocol, operator 2026-06-20).** Always use subagents for substantive work; do not build solo in the main thread.
- Spec first: a Plan/design subagent emits the regression
Alternatives in Security
- Maestro Knowledge — Intent-driven knowledge-store and Run knowledge lifecycle management — audit/prune, stage candidates (with sig 530 ★
- Audit Agent Sessions — Analyze all agent sessions from the last 3 days across Claude, Codex, and Gemini 238 ★
- Migration Agent — Plans a token migration (format, tool, naming or tier): chains token-audit and naming-audit, builds the transf 194 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Engineering Fix
Applies engineering corrections from the last /engineering-audit run. Creates an isolated branch, applies chan
Goalpost
Your agent says “All tests pass!” The hidden tests say 28/34. goalpost makes Claude Code's /goal prove it: fro
Forward Pass Nt
Fresh-eyes whole-app audit — walk the codebase start to finish hunting bugs, security issues, stray code, and
Fix Finding
Auto-fix a specific security finding by editing the IaC file directly
Jiahao
Dual-profile prompt-as-mental-model harness for LLM agents — advisory generator profile in the working agent,
UX A11y
WCAG 2.1 AA accessibility audit plus common-courtesy checks beyond the spec. Produces findings grouped by WCAG
Related Agents
Fresh Eyes Reviewer
First-time reader perspective on a paper. Reads cold with no prior context — not the spec, not the lit review,
Outsider
A fresh-eyes reviewer with no context on prior decisions. Reads an idea, feature, page, or flow the way a firs
History Reviewer
Git history-aware reviewer. Use when changes touch code with non-trivial history, or to check whether a fix ac