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-story-buildernpx skills add hoavdc/CodexKit --skill codexkit-data-story-buildergit 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 | $0.00067 | $0.00711 |
| Opus 5 | $0.00034 | $0.00356 |
| Sonnet 5 | $0.00013 | $0.00142 |
| Haiku 4.5 | $0.00007 | $0.00071 |
Grade A, and why
codexkit-data-story-builder 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Story Builder
Purpose
Make analytics usable by giving the numbers a decision-oriented narrative.
When to use
- A dashboard or KPI movement needs interpretation.
- Experiment results or trend shifts must be explained to leadership.
- A team needs a data-backed narrative, not a raw chart dump.
When not to use
- The task is purely technical modeling with no stakeholder communication output.
- The available data is too weak to support any claims and the user refuses caveats.
Inputs
- business question and target audience
- data points, charts, or KPI movement
- baseline, target, or expected benchmark
- context events that may explain the movement
Procedure
- Start from the business question, not the chart.
- Separate signal, uncertainty, and noise.
- Structure the story as what happened, why it matters, and what to do next.
- Translate numbers into plain-language implications for the chosen audience.
- Recommend the next decision, experiment, or investigation.
- State confidence limits and missing data.
Output
- headline insight
- what changed
- why it matters
- likely drivers or interpretations
- recommended next actions
- caveats and confidence notes
Definition of done
- The audience can act on the analysis.
- The narrative separates evidence from interpretation.
- Caveats are present where the data is weak.
Examples
- "Turn this KPI dashboard into a narrative for the monthly business review."
- "Explain these A/B test results for a non-technical leadership team."
Quality Criteria
- The story starts from a business question, not from chart narration.
- Evidence, interpretation, and recommendation are clearly separated.
- Every claim is supported by a data point, comparison, or stated assumption.
- The "so what" explains business consequence, not just metric movement.
- Caveats and confidence limits are included when data is incomplete or noisy.
Verification (4C)
| Check | Question |
|---|---|
| Correctness | Do the numbers, comparisons, and causal language match the underlying data? |
| Completeness | Does the story include what changed, why it matters, likely drivers, actions, and caveats? |
| Context-fit | Is the narrative useful for the audience's actual decision or operating review? |
| Consequence | What wrong action might a stakeholder take if the story overstates certainty? |
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 · 89 lines · 67 tokens per session scan A 817762e1b7a2
codexkit-data-story-builder is a skill published in the GitHub repository hoavdc/CodexKit (21 stars, last pushed 3mo ago), licensed MIT. It adds 67 tokens to every session and 711 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
knowledge_base
Manage the user's personal knowledge base — knowledge graph, documents, and wiki vault.
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.
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.
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…
detecting-and-responding
蓝队与紫队工程：检测规则编写、SIEM/EDR 调优、事件响应、数字取证、威胁狩猎、ATT&CK 映射、紫队演练闭环。Use when writing Sigma/YARA detection rules, tuning SIEM noise, responding to security incidents, conducting forensic analysis, hunting threats, or running purple team exercises.
securing-cloud-and-supply-chain
云原生与软件供应链安全防御。容器/K8s 加固、Service Mesh、CI/CD 安全、SLSA/SBOM/Sigstore、云 IAM、Secrets 管理、IaC 安全。Use when hardening Kubernetes clusters, auditing CI/CD pipelines, implementing supply chain security, managing cloud IAM, or reviewing IaC code.