Use when multiple requirements or stages risk losing approved scope or completion criteria. Not for ordinary low-risk work.
Scanned 9/12/2026
Install to Claude Code
npx -y skills add semisemil/codex-proofline --skill scope-integrity --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Scope Integrity?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/semisemil-scope-integrity)More formats (shields.io, HTML) on the badges page.
---
name: scope-integrity
description: Use when multiple requirements or stages risk losing approved scope or completion criteria. Not for ordinary low-risk work.
---
# Proofline Scope Integrity
Preserve the user's goal, required outcomes, constraints, and completion criteria throughout the task. Distinguish explicit user-approved changes from implementation choices; an execution plan, assistant summary, or partial result does not replace the user's requirements.
Apply this check directly against the conversation and any authoritative task sources. This skill requires no task record, contract document, or status file.
Resolve failures within authorized scope. If a requirement cannot be met, explain the affected outcome and blocker, continue independent authorized work, and obtain user approval before changing scope or completion criteria. Never silently omit, weaken, or substitute a requirement to make the task appear complete.
Claim completion only when every required outcome is satisfied and supported by the necessary checks. State unmet requirements and unverified checks with their effect on completion; keep optional improvements separate.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
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', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
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