simplify-and-hardenlisted

# Agent Skill: Simplify & Harden Post-completion self-review: clean, harden, and document your work before moving on. Source: https://clawhub.ai/pskoett/simplify-and-harden (v1.0.1, MIT-0, VirusTotal: Benign, OpenClaw: Benign HIGH CONFIDENCE) ## Trigger Conditions Activate automatically when ALL of the following are true: 1. The agent has completed its primary coding task 2. The diff contains a **non-trivial** code change: - Touches at least one executable source file (`*.py`, `*.ts`, `*.js`, `*.go`, `*.rs`, etc.) - AND includes either ≥10 changed non-comment/non-whitespace lines OR at least one high-impact logic change (auth/authz, input validation, data access, external commands, file paths, network requests, concurrency) 3. The skill has not already run on this task (no re-entry loops) **Does NOT activate** when: - The change is docs-only, config-only, comments-only, formatting-only, generated artifacts only, or tests-only - The agent failed or was interrupted - User explicitly skips via `--no-review` ## Scope Constraints **Hard rule: Only touch code modified in this task.** - Do NOT refactor adjacent code that was not modified - Do NOT introduce new dependencies or architectural changes - Flag out-of-scope concerns in the summary output rather than acting on them **Budget limits:** - Maximum additional changes: **20% of the original diff size** (lines changed) - Maximum execution time: **60 seconds** - If either limit is hit, stop and output what you have