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 ymm-oss/fsl --skill fsl-businessgit clone --depth 1 https://github.com/ymm-oss/fslWrote 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/ymm-oss/fsl/fsl-business)<a href="https://agentmods.dev/skills/ymm-oss/fsl/fsl-business"><img src="https://agentmods.dev/badge/skills/ymm-oss/fsl/fsl-business/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/ymm-oss/fsl/fsl-business"><img src="https://agentmods.dev/badge/skills/ymm-oss/fsl/fsl-business.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00098 | $0.01264 |
| Opus 5 | $0.00049 | $0.00632 |
| Sonnet 5 | $0.00020 | $0.00253 |
| Haiku 4.5 | $0.00010 | $0.00126 |
Grade A, and why
fsl-business 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 9d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FSL Business Layer
Use this skill to turn business process material into a business Name { ... }
FSL file. Keep the output at the business/consulting level: process stages,
business transitions, policies, KPIs, goals, and control preservation evidence.
Before writing syntax, read ../fsl/SKILL.md, then use its reference index to
load only the needed language and verifier detail. When working inside this
repository, read examples/consulting/ for As-Is/To-Be work,
examples/pm/cancel_flow.fsl for a PM-friendly business flow, and
examples/e2e/1_business.fsl when this business layer will be chained downstream.
Boundary
Produce business-layer artifacts only:
- A
businessspec withactor,entity,process,transition, optionalcontrol,policy,kpi, andgoal, plus a top-levelverify { instances Entity = N }bound - Optional standalone
governancecatalog when the same controls must be traced across multiple business specs - Verification commands/results, usually
fslc verify ... --engine induction - Optional As-Is/To-Be control preservation using
fslc refineand a mapping file
Do not write system requirements, acceptance criteria, UI states, service/API
shape, data models, queues, outboxes, retry algorithms, implementation adapters, or
design refinement maps from business material. If the source asks for those, route
the work to fsl-requirements or fsl-design after the business layer is agreed.
Workflow
- Extract a business formalization memo in chat:
- actors and external roles
- business entity names and finite
verify { instances ... }modeling sizes - process stages and allowed business transitions
- policies/controls with IDs and verbatim source text
- KPIs/goals and what counts as completion (
kpi name = count Entity in Stage) - open questions about rule priority, exceptions, ownership, or timing
- Ask for confirmation before encoding any interpretation that changes behavior. Representation-only modeling choices may be labeled and carried as comments.
- Write the
businessspec. Prefer readable stage syntax:entity Claimwithverify { instances Claim = 3 }kpi paid_claims = count Claim in Paidcontrol CTRL-1 "..." owner Finance severity high applies_to Claimpolicy POL-1 "..." satisfies CTRL-1 every Case in Source must eventually be Targetpolicy POL-2 "..." satisfies CTRL-1 every Case reaching Completed must have passed through AwaitingApproval— the no-bypass form; desugars to an invisible history flag plus a kernel invariant, without descending torequirementsgoal G "..." some Case can reach Targetgoal G "..." all Case can be Target or OtherTarget
- Run
fslc check, thenfslc verify --engine induction. A pure stage-graph business spec needs no flag for intentional stops:terminal { }is derived automatically from each process's sink stages (stages with no outgoingtransition), so a spec that ends cleanly at those stages verifies with no flag.--deadlock ignoreis not the tool for intended stops — it silences all deadlock detection, including unintended ones. - If comparing As-Is and To-Be, keep them in separate files. Write an explicit
mapping that states the business interpretation, then run
fslc refine tobe.fsl asis.fsl mapping.fsl. - Report results in business language: which policy/control/KPI broke, the shortest reproduction trace, and which interpretation remains a human judgment.
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.
- 9d ago First seen · 91 lines · 98 tokens per session scan A 2c9317d90c16
fsl-business is a skill published in the GitHub repository ymm-oss/fsl (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 98 tokens to every session and 1,264 once invoked, about $0.0005 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
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
stripe-apps
Use when building, modifying, or reviewing a Stripe App — or when the user describes something that implies one (e.g. "add a panel to the customer page", "customize my Stripe Dashboard", "react to Stripe events from my app", "connect my service to Stripe without sharing API keys"). Covers the full app development…
deepseek-harness
Use when building AI agent applications with a plugin-based architecture — Web UI, CLI, Python SDK, Cordis plugin system, multi-model orchestration. DeepSeek Harness (dsh): open-source agent harness by DeepSeek AI where everything is a plugin, powered by Cordis for spatiotemporal composability.
x402
Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…
accelerate
Run PyTorch training across GPUs with minimal changes.
serving-llms-vllm
Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.