Claude skill
Necessity Audit
Necessity Audit is a Claude skill in the Sd0x Harness plugin. Necessity audit for over-designed spec elements.
What it does
The description in the skill's SKILL.md, which Claude reads to decide when to use it:
Necessity audit for over-designed spec elements. Use when: auditing lifecycle spec (1-requirements / 2-tech-spec / 3-architecture) for YAGNI/KISS violations, challenging necessity of FRs/NFRs/abstractions/configs via Codex adversarial debate. Not for: FP reasoning validity (use /codex-review-spec), completeness check (use /feature-completeness), detail review (use /codex-review-doc), or code-level simplification (use /simplify).
The skill's instructions (about 1,373 words) cover:
- Non-Negotiable Rules
- Trigger
- When NOT to Use
- Alternatives by intent
- Chain recommendation
- Arguments
- Workflow
- Phase 0: Preflight (executable)
- Phase A: Claude classify (LLM)
- Phase B: Codex debate (Skill invocation)
- Phase C: Consolidate (executable)
- Assemble + Redact + Emit
How to use it
- Necessity Audit comes inside the Sd0x Harness plugin, so you get it by installing that plugin, along with its 101 other skills. A plugin installs as one unit, with all its skills. The plugin's page has the install steps, and plugins are saved to your Claude account.
- Ask Claude for the task. When your request matches the skill's description, Claude loads it.
- To pick it yourself in Claude chat, type
/or click + and choose necessity-audit. In Claude Code and Cowork, type:/sd0x-dev-flow:necessity-audit
Source
- Plugin
- Sd0x Harness
- SKILL.md
- View on GitHub
- Repo stars
- 196
- Repo last pushed
- Nov 16, 2026
- Checked
- Nov 16, 2026
More skills in Sd0x Harness
- Next StepChange-aware next step advisor. Use when: user asks what to do next, workflow progression is unclear, session just started with dirty worktree.
- Obsidian CLIObsidian vault integration via official CLI.
- Op SessionInitialize 1Password CLI session for Claude Code.
- OrchestrateAgent-driven workflow orchestration (v1 report-only).
- Plan ReviewPre-ExitPlanMode adversarial plan review loop via Codex exec.
- PortfolioPortfolio system knowledge base. Use when: position queries, routing strategy questions, provider integration.
- Post Dev RecapPost-development recap wrapper. Use when: AI/Codex just finished implementing a feature and the user wants a guided walkthrough with scope detection + doc generation + follow-up Q&A.
- Post Dev TestPost-development test completion. Use when: checking test coverage after feature-dev, writing missing integration/e2e tests.
- PR CommentPost friendly review comments to a GitHub PR — prepare locally, preview, then submit as atomic review.
- PR ReviewPR self-review — review changes, produce checklist, update rules
- PR SummaryList open PRs, filter automation PRs, group by ticket ID, format as Markdown. Use when: user asks for PR summary, PR status, or /pr-summary
- Pre PR AuditPre-PR confidence audit with 5-dimension scoring.
- PrecommitPre-commit checks — lint:fix -> build -> test
- Precommit FastQuick pre-commit checks — lint:fix -> test
- Project AuditProject health audit with deterministic scoring.
- Project BriefConvert a technical spec into a PM/CTO-readable executive summary. Simplify technical details, focus on business value.
- Project SetupProject configuration initialization. Use when: first-time setup, auto-detecting framework, replacing CLAUDE.md placeholders.
- Push CiPush to remote and monitor CI. Validates branch safety, executes git push WITH explicit user approval, then monitors CI run status via gh CLI.
- Recap AskInteractive Q&A over an existing recap document.
- Recap DocPost-development recap document generator.
- RefactorMulti-target refactoring orchestrator. Use when: cleaning up messy code/docs, simplifying code, restructuring documents, batch cleanup.
- RemindLightweight model correction with context-aware rule loading.
- Repo IntakeProject initialization inventory (one-time).
- Req AnalyzeRequirements analysis — problem decomposition, stakeholder scan, requirement structuring.