Twin Sparrow Oppus Reasoning Contract — Security skill for Claude Code
Enforce disciplined reasoning structure for research, architecture, audit, spec review, implementation planning, evidence evaluation, and tasks requiring explicit assumptions and claim boundaries.
How to install Twin Sparrow Oppus Reasoning Contract
Installs to ~/.claude/skills/lesz-xi-companion-adapter-twin-sparrow-oppus-reasoning-contract/SKILL.md
mkdir -p ~/.claude/skills/lesz-xi-companion-adapter-twin-sparrow-oppus-reasoning-contract && curl -fsSL https://raw.githubusercontent.com/Lesz-Xi/companion-adapter/HEAD/commands/twin-sparrow-oppus-reasoning-contract.md -o ~/.claude/skills/lesz-xi-companion-adapter-twin-sparrow-oppus-reasoning-contract/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Twin Sparrow Oppus Reasoning Contract does
description: "Enforce disciplined reasoning structure for research, architecture, audit, spec review, implementation planning, evidence evaluation, and tasks requiring explicit assumptions and claim boundaries." argument-hint: ""
/twin-sparrow-oppus-reasoning-contract
Apply the **oppus-reasoning-contract** skill from the Twin-Sparrow skill registry.
Usage
/twin-sparrow-oppus-reasoning-contract $ARGUMENTS
If arguments a
Alternatives in Security
- Security Threat Model — Generate repo-specific threat models identifying trust boundaries 14.6k ★
- Eval Audit — /eval-audit — Batch Skill Evaluation 216 ★
- Claudit Sec — Security audit tool for Claude Desktop and Claude Code on macOS — single-command visibility into MCP servers 115 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Twin Sparrow Deep Audit
Composite deep audit skill combining expert-engineer, code-quality-skill, and oppus-reasoning-contract for str
WCAG Accessibility Skills
WCAG 2.1/2.2 accessibility audit CLI and AI skill with explicit manual-review boundaries.
Yotta Security Testing
YuanCe (元测) — disciplined authorization-first security-testing methodology for AI agents: four-stage web secur
Platform Check
/platform-check — Audit code for cross-platform assumptions
Ops Audit
Audit an existing Claude Code harness for runtime assumptions, operational debt, and failure recovery gaps (se
Consistency Check
Audit a doc bundle for cross-reference integrity, count drift, pronoun ambiguity, audience assumptions, and ot
Related Agents
Selfish Orchestrator
Coordinate the system, route work to specialists, synthesize conflicts, and enforce human approval boundaries.
Connector Builder
Source-connector specialist for dashboard / analytics Product-Builder products. The read-side twin of integrat
Implementer Expert Agent
Expert implementation worker for spec-driven development. Use ONLY for hard tasks requiring deep reasoning — c