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-buy-vs-build)<a href="https://agentmods.dev/skills/geledek/enterprise-ai-transformation-skills/tech-buy-vs-build"><img src="https://agentmods.dev/badge/skills/geledek/enterprise-ai-transformation-skills/tech-buy-vs-build/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-buy-vs-build"><img src="https://agentmods.dev/badge/skills/geledek/enterprise-ai-transformation-skills/tech-buy-vs-build.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 | $0.00120 | $0.01478 |
| Opus 5 | $0.00060 | $0.00739 |
| Sonnet 5 | $0.00024 | $0.00296 |
| Haiku 4.5 | $0.00012 | $0.00148 |
Grade A, and why
tech-buy-vs-build 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech — Buy vs. Build (AI Sourcing)
Decide whether to build AI capability in-house, buy from a vendor, or partner. Applies NANDA's empirical 2:1 buy advantage and a vendor-archetype selection framework.
The principle: Buy the model. Build the orchestration. Foundation models commoditize — the moat lives in orchestration, workflow design, and the skill library. (Consult nanda-tech-buy-vs-build.md and andrew-ng-three-moats.md.)
Output contract (stable): per-component Buy / Build verdicts plus an overall investment verdict.
Role 1: Map the Decision
Not all AI investment is the same decision. First, classify what is being sourced.
COMPONENT CLASSIFICATION — for each component being decided, classify:
- Foundation model capability (GPT-level reasoning, multimodal, code generation) → almost always BUY
- Orchestration / workflow automation → BUILD for the parts that encode your processes; BUY platforms where commodity works
- Fine-tuned or domain-specific model → BUILD (on top of a bought base) only if the domain is genuinely proprietary
- End-user application / interface → often BUY (SaaS or API), with customization built in-house
- Data infrastructure → BUILD (it is company-specific; no vendor can own your data strategy)
- Skill library / process knowledge → BUILD (this is the moat — consult
hiten-skill-library.md)
Output a component map: for each component, state the type and initial BUY/BUILD instinct before analysis.
Output: COMPONENT | TYPE | INITIAL INSTINCT
Role 2: The 2:1 Evidence Test
MIT NANDA 2025 finding: firms that buy AI capability vs. build it internally are 2× more likely to capture value. (Consult 95-5-genai-divide.md)
For each BUY candidate, confirm the buy rationale holds:
- Does an existing vendor solution cover ≥80% of the use case? If no: buying may not solve the problem.
- Is the build effort primarily in the model, or in integration and workflow? If model: buy. If integration/workflow: that's a build regardless.
- Is the value in having this model, or in what you do with it? If value is in the doing: buying the model is the input, not the output.
- Is this a commodity capability or a differentiating capability? Commodity = buy. Differentiating = evaluate carefully.
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 · 123 lines · 120 tokens per session scan A 827fdd846696
tech-buy-vs-build is a skill published in the GitHub repository geledek/enterprise-ai-transformation-skills (9 stars, last pushed 2mo ago), licensed MIT. It adds 120 tokens to every session and 1,478 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
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…
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…
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…
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…
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.
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.