Skill

Audit Fleet SQL Todos

This skill should be used when coordinating audit-fleet progress with SQL todo tracking and contract-aware completion gates across all audit lanes.

From audit-fleet

Install

Run in your terminal

npx claudepluginhub nsalvacao/nsalvacao-claude-code-plugins --plugin audit-fleet

Tool Access

This skill uses the workspace's default tool permissions.

Skill Content

Similar Skills

agent-payment-x402

Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.

ecc

140.3k

agent-harness-construction

Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.

ecc

140.3k

agent-eval

Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.

ecc

140.3k

Stats

Parent Repo Stars0

Parent Repo Forks0

Last CommitMar 18, 2026

Actions

View Source View Plugin View on GitHub View README

Canonical Contract Terms

All audit-fleet outputs must preserve this exact section order:

Executive Summary

Findings

Quick Wins

High-Impact Expansions

All Findings entries must include these keys exactly:

finding_id

severity

dimension

evidence

impact

recommendation

effort

owner

dependencies

confidence

acceptance_criteria

Severity enum is strict: critical | warning | info.

Workflow

Create one todo per lane plus one consolidation todo.

Move todo to in_progress before lane work starts.

Validate lane report has Executive Summary, Findings, Quick Wins, High-Impact Expansions.

Validate every Findings row includes finding_id, severity, dimension, evidence, impact, recommendation, effort, owner, dependencies, confidence, acceptance_criteria.

Mark lane done only after severity values are critical | warning | info and audit-only behavior is respected.

Audit Fleet SQL Todos

Track lane progress with SQL so audit runs remain resumable, dependency-aware, and contract-compliant.

Canonical Contract Terms

All audit-fleet outputs must preserve this exact section order:

Executive Summary
Findings
Quick Wins
High-Impact Expansions

All Findings entries must include these keys exactly:

finding_id
severity
dimension
evidence
impact
recommendation
effort
owner
dependencies
confidence
acceptance_criteria

Severity enum is strict: critical | warning | info.

Trigger Cues

Use when requests mention:

track lane status
resume interrupted audit
dependency-aware lane execution

Workflow

Create one todo per lane plus one consolidation todo.
Move todo to in_progress before lane work starts.
Validate lane report has Executive Summary, Findings, Quick Wins, High-Impact Expansions.
Validate every Findings row includes finding_id, severity, dimension, evidence, impact, recommendation, effort, owner, dependencies, confidence, acceptance_criteria.
Mark lane done only after severity values are critical | warning | info and audit-only behavior is respected.

Dependency Rule

Consolidation todo depends on all specialist lane todos.