Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/bestagentkits/agency-skillsnpx agentmods add skills/bestagentkits/agency-skills/cdo-reviewWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bestagentkits/agency-skills/cdo-review)<a href="https://agentmods.dev/skills/bestagentkits/agency-skills/cdo-review"><img src="https://agentmods.dev/badge/skills/bestagentkits/agency-skills/cdo-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bestagentkits/agency-skills/cdo-review"><img src="https://agentmods.dev/badge/skills/bestagentkits/agency-skills/cdo-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00069 | $0.01250 |
| Opus 5 | $0.00034 | $0.00625 |
| Sonnet 5 | $0.00014 | $0.00250 |
| Haiku 4.5 | $0.00007 | $0.00125 |
Grade A, and why
cdo-review 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 9d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cs:cdo-review — CDO Forcing Questions
Command: /cs:cdo-review <plan>
The decision-driven CDO pressure-tests any plan that touches data strategy. Six questions before any commitment to a data architecture, AI training run, data productization, or data team hire.
When to Run
- Before approving any new ML model training run that uses customer data
- Before signing a multi-year data-infrastructure SaaS contract (Snowflake, Databricks, Fivetran)
- Before productizing any customer data (benchmark report, embedding endpoint, license)
- Before a major data team hire (head of data, CDO, data PM, ML engineer)
- Before M&A diligence — yours or theirs
- When the founder uses the word "monetize" near "data"
The Six CDO Questions
1. What decision does this data drive?
If no decision is unblocked, why are we collecting / training on / productizing it?
- "We might need it later" is not a decision.
- "It feels like a moat" is not a decision.
- A real answer names a specific business call that requires this data.
2. What's the consent provenance for every source?
For each data source: origin, consent flow, data class, intended use.
- 1st-party-TOS-only is weaker than 1st-party-explicit-opt-in.
- Bundled TOS doesn't cover material new purposes (training on PII for foundation models).
- Run
ai_training_data_audit.pyif there's any AI use case in scope.
3. Who consumes this internally — and how many distinct functional domains?
Drives the centralize-vs-embed and warehouse-vs-mesh decisions.
- <5 consumers: warehouse-only.
- 5-25 consumers: lakehouse.
- 25+ consumers + federated culture: mesh.
- Premature architecture choice is the #1 cause of data-team burnout.
4. What's the M&A diligence impact?
If an acquirer asks about this data corpus tomorrow, are we ready?
- Is there a documented anonymization process?
- What % of customers have MSA carve-outs?
- Are training-data provenance logs current?
- Run
data_asset_valuator.pyquarterly.
What ships with it
1 file 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.
- 9d ago First seen · 127 lines · 69 tokens per session scan A 65e31b0a6d98
cdo-review is a skill published in the GitHub repository bestagentkits/agency-skills (11 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 1,250 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 2026-09-03.
Other skills, from other repositories
analyze-generative-diffusion-model
Analyze pre-trained generative diffusion models (Stable Diffusion, DALL-E, Flux) by computing quality metrics (FID, IS, CLIP score, precision/recall), inspecting noise schedules, extracting and visualizing attention maps, and probing latent spaces. Use when evaluating a pre-trained generative diffusion model's output…
deploy-edge-ai-model
Deploy machine learning models to edge devices using Google AI Edge Gallery, TensorFlow Lite, ONNX Runtime, and MediaPipe. Covers model quantization (INT8/INT4), on-device inference with Gemma 4 models, Android/iOS deployment via AI Edge Gallery, hardware delegate selection (GPU/NPU/DSP), and performance benchmarking…
build-feature-store
Build a feature store using Feast for centralized feature management, configure offline and online stores for batch and real-time serving, define feature views with transformations, and implement point-in-time correct joins for ML pipelines. Use when managing features for multiple ML models, ensuring training-serving…
deploy-ml-model-serving
Deploy machine learning models to production serving infrastructure using MLflow, BentoML, or Seldon Core with REST/gRPC endpoints, implement autoscaling, monitoring, and A/B testing capabilities for high-performance model inference at scale. Use when deploying trained models for real-time inference, setting up REST…
design-serialization-schema
Design serialization schemas using JSON Schema, Protocol Buffer definitions, or Apache Avro. Covers schema versioning, backwards compatibility, validation rules, and evolution strategies for long-lived data formats. Use when defining a new API contract or data interchange format, adding fields to an existing schema…
数据搬运工
A general data-transfer and format-conversion tool for moving, cleaning, and reshaping files. It works with spreadsheets, CSV and TSV tables, JSON, XML, YAML, SQL inserts, and SQLite databases.