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 skills add TIBCOSoftware/flogo-enterprise-hub --skill agentic-ai-use-case-buildergit clone --depth 1 https://github.com/TIBCOSoftware/flogo-enterprise-hubWrote 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/tibcosoftware/flogo-enterprise-hub/agentic-ai-use-case-builder)<a href="https://agentmods.dev/skills/tibcosoftware/flogo-enterprise-hub/agentic-ai-use-case-builder"><img src="https://agentmods.dev/badge/skills/tibcosoftware/flogo-enterprise-hub/agentic-ai-use-case-builder/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/tibcosoftware/flogo-enterprise-hub/agentic-ai-use-case-builder"><img src="https://agentmods.dev/badge/skills/tibcosoftware/flogo-enterprise-hub/agentic-ai-use-case-builder.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 | $0.00427 | $0.07685 |
| Opus 5.5 | $0.00171 | $0.03074 |
| Sonnet 5.5 | $0.00085 | $0.01537 |
| Haiku 4.5 | $0.00043 | $0.00768 |
Grade A, and why
agentic-ai-use-case-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 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 — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic AI Use Case Builder (governed by default)
Builds an agentic AI demo that would survive a customer's architecture review: agentic in the middle, deterministic at the edges. The LLM handles the conversation and the one genuinely semantic step. The database decides identity, eligibility, prices and state changes. People decide anything they must answer for.
This is the single, self-contained, canonical skill for building agentic AI on TIBCO Flogo. It carries all its own build machinery (the fda recipes, the PostgreSQL activity contract, the base validator, the manual-config gap) and depends on no other skill. Governance is the default style, and you build it with either of two methods (Phase 0a asks which): FDA-CLI from scratch (recommended) or clone-and-adapt from a governed reference app. The table below shows what governance adds over a plain, ungoverned demo:
| plain ungoverned demo | this builder (governed default) | |
|---|---|---|
| Starting point | a domain | a domain + the decision-framework gate (every operation classified first) |
| Reads | one tool per table | scoped by a session token through a rule function |
| Writes | A2A agents write with LLM-chosen values | guarded MCP tools: INSERT … SELECT rule_fn(), plus readback of outcome and reason |
| State changes | one call | two-step propose → user yes → confirm (15-minute expiry, rules rechecked) |
| Exceptions | the model decides | human-owned open_review_case, routed by a table, then decided by a staff reviewer in the same chat (team scope + approval limit in SQL) |
| A2A agents | action agents | reasoning agents with minimised, read-only input |
| Identity | none / trust the chat | verify_* → session token; per-connection conversationId |
| Done means | design-time validation | 4-step test ladder, including prompt injection |
Worked example: samples/Agentic_AI/Industry_Use_Cases/Media_Travel/Media_Publishing/Scholarly_Publishing_Author_Services_Use_Case/. Read its
database.sql, _rebuild/tool_spec.py and README.md before building a new one. For the reviewer loop, read
the "THE REVIEWER LOOP" block of Financial_Services/Banking/Retail_Banking_Assistant_Use_Case/database.sql and
governed-patterns.md §9.
What ships with it
30 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.
- README.md 16 KB
- references/chatbot-test.md 1.7 KB
- references/connector-prereqs.md 13 KB
- references/data-and-docs.md 8.0 KB
- references/decision-framework-gate.md 5.7 KB
- references/discovery-questions.md 9.6 KB
- references/fda-build-recipes.md 34 KB
- references/fda-limitations.md 6.8 KB
- references/flogo-app-templates.md 14 KB
- references/governed-patterns.md 35 KB
- references/industry-taxonomy.md 3.8 KB
- references/manual-config-gap.md 9.0 KB
- references/port-registry.md 5.0 KB
- references/postgres-activity-patterns.md 21 KB
- references/runtime-gotchas.md 9.7 KB
- references/spec-and-readme-template.md 9.8 KB
- references/testing-ladder.md 16 KB
- references/use-case-spec-template.md 7.2 KB
- references/validate_flogo_apps.py 15 KB runs code
- references/validate_governed_apps.py 22 KB runs code
- templates/_rebuild/a2a_smoke.py 7.4 KB runs code
- templates/_rebuild/build_agents.py 14 KB runs code
- templates/_rebuild/build_mcp.py 7.9 KB runs code
- templates/_rebuild/build_orchestrator.py 14 KB runs code
- templates/_rebuild/chat_e2e.py 21 KB runs code
- templates/_rebuild/fda_common.py 10 KB runs code
- templates/_rebuild/mcp_smoke.py 11 KB runs code
- templates/_rebuild/test_rules.py 29 KB runs code
- templates/_rebuild/tool_spec.py 20 KB runs code
- templates/preflight.py 18 KB runs code
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 Changed 6419785c7f9e
- 13d ago First seen · 364 lines · 427 tokens per session scan A 905dbd8ffe09
agentic-ai-use-case-builder is a skill published in the GitHub repository TIBCOSoftware/flogo-enterprise-hub (14 stars, last pushed 13d ago), licensed Apache-2.0. It adds 427 tokens to every session and 7,685 once invoked, about $0.0017 per session on Opus 5.5. 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 2026-10-17.
Other skills, from other repositories
deepstream-sop
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the…
neuron-agent
Create, configure, and extend Neuron AI agents in PHP using providers, tools, chat history, memory, and custom workflow nodes. Use for Neuron Agent implementation, configuration, conversation lifecycle, and input/output extensions.
vllm
Deploy and serve LLMs with vLLM behind an OpenAI-compatible endpoint, with tool calling enabled for agent workloads.
llm-pipeline
Use when wiring several LLM calls into a production flow: typed contracts between steps, a router/gateway so 429s, timeouts and outages fail over instead of taking you down, and cost control via caching, model tiers and abort caps. NOT single-prompt wording (that is prompt-engineering), NOT a model-driven tool loop…
model-serving-and-monitoring
Use when a model is served online (FastAPI, BentoML) or scored in batch, when changing how a model artifact is loaded or versioned, or when adding drift, quality or prediction monitoring and a rollout plan for a new model.
data-streaming
Designs streaming platforms for Kafka, Flink, CDC, and lakehouse ingestion. Use when planning event backbones, CDC pipelines, schema governance, or real-time lakehouse delivery.