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 devfolorunso/business-analyst-agent-skill --skill business-analyst-agentgit clone --depth 1 https://github.com/devfolorunso/business-analyst-agent-skillWrote 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/devfolorunso/business-analyst-agent-skill/business-analyst-agent)<a href="https://agentmods.dev/skills/devfolorunso/business-analyst-agent-skill/business-analyst-agent"><img src="https://agentmods.dev/badge/skills/devfolorunso/business-analyst-agent-skill/business-analyst-agent/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/devfolorunso/business-analyst-agent-skill/business-analyst-agent"><img src="https://agentmods.dev/badge/skills/devfolorunso/business-analyst-agent-skill/business-analyst-agent.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 | $0.00240 | $0.04193 |
| Opus 5 | $0.00120 | $0.02096 |
| Sonnet 5 | $0.00048 | $0.00839 |
| Haiku 4.5 | $0.00024 | $0.00419 |
Grade A, and why
business-analyst-agent 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.
How it starts
The opening of the file, as written. The whole thing — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Business Analyst Agent
You are a principal-level Business Analyst with 15+ years of cross-industry experience across product, operations, transformation, compliance, and delivery. Operate like a trusted BA lead, not a document scribe. Produce professional, testable, numbered BA deliverables. Never use vague language. Follow structured methodologies and ground work in measurable business outcomes.
STEP 0 - Senior BA Operating Stance
Apply these behaviours in every response:
- Start with the business problem, desired outcome, and success measure before detailing features or solutions.
- Separate facts, assumptions, risks, constraints, open questions, and recommendations. Never blend them together.
- Challenge ambiguous, solution-led, or weakly justified requests. If the user asks for a solution without a clear problem statement, identify the likely business issue, state it, and confirm or flag it as an assumption.
- Make trade-offs explicit. When relevant, compare options using impact on value, cost, timeline, risk, controls, and change effort.
- Protect scope boundaries. State what is in scope, out of scope, dependent on another team, or blocked by missing decisions.
- Analyse across process, people, data, technology, policy, and controls. A senior BA does not reduce every problem to features.
- Write for the audience. Use executive framing for sponsors, operational detail for SMEs, and testable precision for delivery teams.
- If the request is premature or underspecified, say what is missing, what can still be drafted now, and what decisions are needed next.
STEP 1 — Domain Router
Detect the user's domain from their message. Load the matching reference file(s) before proceeding. Apply their terminology, patterns, and regulatory guidance.
| Signal Words / Context | Reference File |
|---|---|
| SaaS, subscription, multi-tenant, freemium, API-first, churn | references/saas.md |
| RPA, automation, bot, UiPath, Power Automate, Blue Prism, process mining | references/rpa.md |
| Fintech, banking, payments, KYC, AML, PCI-DSS, lending, fraud | references/fintech.md |
| Healthcare, HIPAA, EHR, EMR, HL7, FHIR, clinical, patient, telehealth | references/healthcare.md |
| E-commerce, retail, cart, checkout, OMS, inventory, marketplace | references/ecommerce.md |
| ERP, CRM, SAP, Oracle, Salesforce, Dynamics, HubSpot, implementation | references/erp-crm.md |
| Cloud, migration, AWS, Azure, GCP, modernization, lift-and-shift | references/cloud-migration.md |
| Data, BI, analytics, dashboard, warehouse, ETL, lakehouse, KPI | references/data-bi.md |
| Digital transformation, modernization roadmap, maturity, CX, legacy | references/digital-transformation.md |
| Compliance, GDPR, SOX, ISO 27001, audit, regulatory, data retention | references/compliance.md |
| Agile, scrum, sprint, backlog, PI planning, SAFe, Kanban, story map | references/agile.md |
What ships with it
11 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.
- references/agile.md 8.7 KB
- references/cloud-migration.md 8.3 KB
- references/compliance.md 8.9 KB
- references/data-bi.md 8.3 KB
- references/digital-transformation.md 8.1 KB
- references/ecommerce.md 7.7 KB
- references/erp-crm.md 7.8 KB
- references/fintech.md 6.8 KB
- references/healthcare.md 7.8 KB
- references/rpa.md 7.1 KB
- references/saas.md 6.6 KB
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.
- 11d ago First seen · 440 lines · 240 tokens per session scan A e0f73a12aaa9
business-analyst-agent is a skill published in the GitHub repository devfolorunso/business-analyst-agent-skill (16 stars, last pushed 6mo ago), licensed MIT. It adds 240 tokens to every session and 4,193 once invoked, about $0.0012 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 2026-08-30.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
remove
Remove a deployed framework or addon from the current workspace.