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.
/plugin marketplace add geledek/enterprise-ai-transformation-skills/plugin install enterprise-ai-transformation-skillsWrote 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/geledek/enterprise-ai-transformation-skills/tech-stack-diagnostic)<a href="https://agentmods.dev/skills/geledek/enterprise-ai-transformation-skills/tech-stack-diagnostic"><img src="https://agentmods.dev/badge/skills/geledek/enterprise-ai-transformation-skills/tech-stack-diagnostic/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/geledek/enterprise-ai-transformation-skills/tech-stack-diagnostic"><img src="https://agentmods.dev/badge/skills/geledek/enterprise-ai-transformation-skills/tech-stack-diagnostic.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 | $0.00127 | $0.02028 |
| Opus 5 | $0.00063 | $0.01014 |
| Sonnet 5 | $0.00025 | $0.00406 |
| Haiku 4.5 | $0.00013 | $0.00203 |
Grade A, and why
tech-stack-diagnostic 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 12d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech — AI Stack Diagnostic
Diagnose the full enterprise AI technology stack across six layers. The model is the smallest part of the problem. Data and orchestration are where most organizations are blocked.
Walk each layer. Score it. Surface the weakest link. A chain breaks where the weakest link breaks — and most chains break at data or orchestration, not at the model.
Output contract (stable): six per-layer scores (STRONG / ADEQUATE / GAP / BLOCKING), naming the single weakest layer and its remediation priority.
Layer 1: Data Foundation
Core question: Is data AI-ready, or does it "should exist"?
Stanford AI Index 2026: data engineers and software engineers are tied as the most in-demand AI role. The limiting factor in enterprise AI is data pipeline readiness — not model access. For every $1 of visible tech investment, up to $10 is invisible — mostly data and change management.
Assess:
- Existence: Does the required data exist in a usable format? (Not "does it exist somewhere in the enterprise?")
- Access: Is there a data pipeline that delivers this data to AI systems in production? (Not just in a notebook)
- Quality: What are the null rates, duplicate rates, freshness, and provenance characteristics?
- Rights: Does the organization have confirmed legal rights to use this data for AI? (GDPR, training data rights, contractual restrictions)
- Unity: Is data unified across functions, or siloed in 50+ databases controlled by 50+ VPs? (The Ng Unified Data Warehouse prerequisite — consult
isg-data-foundation.md)
Score: STRONG / ADEQUATE / GAP / BLOCKING Note: if BLOCKING, nothing in layers 2–6 will compound. Fix this first.
Output: DATA EXISTENCE | DATA ACCESS | DATA QUALITY | DATA RIGHTS | DATA UNITY | LAYER 1 SCORE
Layer 2: Model Selection and Lifecycle
Core question: Is the model decision appropriate, and is there a management process?
Key framing: foundation models commoditize. The strategic question is orchestration, not which model to buy or train. Over-optimization of the model layer at the expense of layers 3–6 is the most common misallocation.
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.
- 12d ago First seen · 176 lines · 127 tokens per session scan A 1ab7ac96aa58
tech-stack-diagnostic is a skill published in the GitHub repository geledek/enterprise-ai-transformation-skills (9 stars, last pushed 2mo ago), licensed MIT. It adds 127 tokens to every session and 2,028 once invoked, about $0.0006 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.
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…
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…
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…
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.
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…
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.