tech-data-deployment

tech-data-deployment is a skill for Claude Code from geledek/enterprise-ai-transformation-skills. It costs 179 tokens per session (2,934 once invoked), scanned A, original, MIT.

A skill for deciding where an AI workflow should run based on the sensitivity of its data. It compares options such as consumer ChatGPT, enterprise software, a private cloud environment, or a system disconnected from outside networks.

In plain words
What is it for?
Use it to classify data, choose an appropriate deployment setup, assess regulatory risk, and define the security controls needed for each data class.
Why use it?
It helps prevent sensitive information from being sent to an unsuitable AI service and gives teams a consistent way to handle unauthorised AI use.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the enterprise-ai-transformation-skills plugin — 16 skills shipped together

Good fit Use it to classify data, choose an appropriate deployment setup, assess regulatory risk, and define the security controls needed for each data class.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add geledek/enterprise-ai-transformation-skills
Claude Code
/plugin install enterprise-ai-transformation-skills

Made for: Claude Code.

Or install enterprise-ai-transformation-skills, the plugin that ships this one along with the rest of its 16 skills.

Wrote 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.

agentmods badge for tech-data-deployment

README.md
[![agentmods](https://agentmods.dev/badge/skills/geledek/enterprise-ai-transformation-skills/tech-data-deployment/github.svg)](https://agentmods.dev/skills/geledek/enterprise-ai-transformation-skills/tech-data-deployment)
Your own site
<a href="https://agentmods.dev/skills/geledek/enterprise-ai-transformation-skills/tech-data-deployment"><img src="https://agentmods.dev/badge/skills/geledek/enterprise-ai-transformation-skills/tech-data-deployment/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.

agentmods 80×15 button for tech-data-deployment

Your own site · 80×15
<a href="https://agentmods.dev/skills/geledek/enterprise-ai-transformation-skills/tech-data-deployment"><img src="https://agentmods.dev/badge/skills/geledek/enterprise-ai-transformation-skills/tech-data-deployment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 179 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,934 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00179 $0.02934
Opus 5 $0.00089 $0.01467
Sonnet 5 $0.00036 $0.00587
Haiku 4.5 $0.00018 $0.00293

Measured 11d ago against content hash f5b061ed465c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

tech-data-deployment 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 11d 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.

skills/tech-data-deployment/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tech — Data-Trust Deployment Pattern

A four-dimension assignment of data sensitivity class to deployment pattern with explicit per-tier controls. Anchored to NIST AI RMF (GOVERN/MAP/MEASURE/MANAGE), ISO/IEC 42001, EU AI Act risk tiers, and IMDA Model AI Governance Framework + GenAI Companion.

Empirical anchor: BCG 2025 broad-use-vs-value 88/25 gap — 88% of organizations use AI broadly, only ~25% capture material value; the gap is largely a data-trust and deployment-pattern gap, not a model gap. (A different BCG 88/25 finding — manager role-modeling — is cited in people-readiness-conversation and people-literacy-curriculum; always read "88/25" here as broad-use-vs-value.) MIT 95% — most enterprise GenAI pilots fail to reach production, and shadow-AI usage runs ~2x sanctioned usage in the surveyed cohort.

Verdict vocabulary (stable output contract): Approved / Conditional / Blocked, with assigned deployment tier and per-tier control checklist.


Dimension 1: Data Sensitivity Classification

Core question: What class of data does this workflow actually touch — and which regulatory regime governs it?

Classify the data INPUT, the data IN-FLIGHT (prompt + retrieval), and the data OUTPUT separately. The most sensitive of the three sets the tier.

CLASS LADDER (assign one):

  1. PUBLIC — already published; no confidentiality cost if exposed.
  2. INTERNAL — non-public business data, low individual harm if leaked (org charts, internal docs, generic SOPs).
  3. CONFIDENTIAL — commercially sensitive (M&A, pricing, source code, unreleased product, supplier contracts, legal privilege).
  4. REGULATED — named regime applies. Identify which:
    • PII under GDPR (EEA), PDPA (SG), CCPA (CA)
    • PHI under HIPAA (US health) — requires BAA
    • PCI-DSS (cardholder data)
    • MNPI under MAS (SG financial), MiFID II (EU), SEC Reg FD (US)
    • Student records under FERPA (US education) / equivalent
    • Cross-border transfer triggers — GDPR Chapter V, China PIPL, India DPDP

Read the full file on GitHub · 193 lines

Files

What ships with it

2 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.

Changes

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.

  1. 11d ago First seen · 193 lines · 179 tokens per session scan A f5b061ed465c

Subscribe to this mod's changes

tech-data-deployment is a skill published in the GitHub repository geledek/enterprise-ai-transformation-skills (9 stars, last pushed 2mo ago), licensed MIT. It adds 179 tokens to every session and 2,934 once invoked, about $0.0009 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 2026-08-31.

Related

Other skills, from other repositories

visualize

Visualize the Semantica knowledge graph — topology, centrality, communities, paths, embeddings, decision insights, and temporal evolution. Uses GraphAnalyzer, CentralityCalculator, CommunityDetector, PathFinder, and ContextGraph analytics. Sub-commands: topology, centrality, community, path, decision-graph, insights…

semantica-agi/semantica · 0 tokens

embed

Generate, inspect, and use node/text embeddings in Semantica — compute Node2Vec embeddings, find similar nodes, score link predictions, batch similarity, and pairwise similarity. Uses NodeEmbedder, SimilarityCalculator, LinkPredictor, and AgentContext. Sub-commands: compute, similar, similarity, predict-link…

semantica-agi/semantica · 0 tokens

reason

Run reasoning over the Semantica knowledge graph — deductive logic, abductive hypothesis generation, Datalog programs, SPARQL queries, Rete network evaluation. Uses DeductiveReasoner, AbductiveReasoner, DatalogReasoner, SPARQLReasoner, ReteEngine. Sub-commands: deductive, abductive, datalog, sparql, rete, prove…

semantica-agi/semantica · 0 tokens

validate

Validate Semantica pipelines, extraction quality, graph schemas, and ontology consistency. Returns structured error/warning checklists. Uses PipelineValidator, PipelineBuilder.validatepipeline(), GraphValidator, and OntologyValidator. Sub-commands: pipeline, step, dependencies, extraction, graph, ontology, performance.

semantica-agi/semantica · 0 tokens

temporal

Temporal graph operations on Semantica — scoped queries at a point in time, graph snapshots, node change timelines, temporal causal analysis, and graph state reconstruction. Uses AgentContext.findprecedents(asof=), ContextGraph.stateat(), CausalChainAnalyzer.traceattime(), and TemporalQueryRewriter. Sub-commands…

semantica-agi/semantica · 0 tokens

extract

Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.

semantica-agi/semantica · 59 tokens