Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/hoavdc/codexkit/codexkit-data-quality-auditornpx skills add hoavdc/CodexKit --skill codexkit-data-quality-auditorgit clone --depth 1 https://github.com/hoavdc/CodexKitWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00069 | $0.01173 |
| Opus 5 | $0.00034 | $0.00587 |
| Sonnet 5 | $0.00014 | $0.00235 |
| Haiku 4.5 | $0.00007 | $0.00117 |
Grade A, and why
codexkit-data-quality-auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Quality Auditor
When to Use
- Before building analytics or dashboards on a new data source
- When data issues cause downstream report errors
- During data migration or system integration
- When establishing data quality monitoring rules
Procedure
Step 1 — Scope & Profiling
Identify the dataset and context:
- Table/file name, row count, column count
- Business purpose: what decisions does this data support?
- Data owner: who is accountable?
Profile the data:
- Column types (string, numeric, date, boolean, null)
- Null rates per column
- Distinct value counts
- Min/Max/Mean for numerics
- Date range coverage
Step 2 — Six-Dimension Assessment
Score each dimension 1–5:
| Dimension | Question | Score Method |
|---|---|---|
| Completeness | Are all required fields populated? | % non-null for required fields |
| Accuracy | Do values represent reality? | Sample validation against source |
| Consistency | Do related fields agree? | Cross-field rule checks |
| Timeliness | Is data current enough for its purpose? | Max staleness vs requirement |
| Validity | Do values conform to allowed ranges/formats? | Format + range validation |
| Uniqueness | Are there unwanted duplicates? | Duplicate rate on key columns |
Step 3 — Issue Log
For each issue found:
| # | Dimension | Column(s) | Issue Description | Severity | Records Affected | Example |
|---|---|---|---|---|---|---|
| 1 | Completeness | 12% null in required field | High | 1,200 | row 45: null |
Severity: Critical (blocks use) / High (degrades quality) / Medium (cosmetic) / Low (nice-to-fix)
Step 4 — Remediation Plan
For each Critical/High issue:
| Issue | Root Cause | Fix | Owner | Deadline |
|---|---|---|---|---|
| Missing emails | Optional in old form | Backfill from CRM | Data Eng | Sprint 4 |
Step 5 — Monitoring Rules
Define ongoing quality checks:
- Automated checks to run on each data load
- Alerting thresholds (if quality drops below X%, alert owner)
- Review cadence (weekly, monthly)
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 143 lines · 69 tokens per session scan A 89933a5a0837
codexkit-data-quality-auditor is a skill published in the GitHub repository hoavdc/CodexKit (21 stars, last pushed 3mo ago), licensed MIT. It adds 69 tokens to every session and 1,173 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
reducing-aigc-detection
Systematically reduce AIGC detection rates in academic papers (Chinese/English). Analyzes detection reports, identifies high-impact sections, applies multi-layer rewriting strategies preserving formatting/footnotes, and verifies results. Supports 维普/知网/Turnitin platforms.
defending-applications
Application security defense knowledge for builders. Covers Web/API/GraphQL hardening (XSS/SQLi/SSRF/IDOR/BOLA/Mass Assignment/deserialization/upload/path traversal), authentication/authorization (OAuth 2.0/OIDC/JWT/Session/Cookie/SAML/SSO), and LLM application security (prompt injection, jailbreak, RAG poisoning…
verification-loop
Evidence-before-assertions workflow. Use before claiming work is done, before release, and after any behavior change in scripts/skills/MCP.
analyzing-security
Scans code for security vulnerabilities, detects dangerous patterns, and ensures security decisions are documented. Use when running security scans, auditing code, or checking for OWASP issues, injection risks, or sensitive data leaks. Automatically triggered on new modules, security-related changes, or post-refactor.
architecting-security
安全架构与治理：威胁建模 (STRIDE/PASTA/LINDDUN)、零信任身份架构、IAM/SSO/MFA/PAM、合规框架 (SOC2/PCI/HIPAA/GDPR)、DLP、隐私工程、安全控制设计。Use when designing security architecture, threat modeling new systems, implementing zero-trust identity, designing IAM/SSO/PAM, building compliance evidence chains, or planning privacy-by-design.
building-agent-systems
AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt injection, jailbreak defense, output filtering), RAG architecture (chunking, hybrid retrieval, rerank), and prompt…