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 rjmurillo/ai-agents --skill business-strategygit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/rjmurillo/ai-agents/business-strategy)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/business-strategy"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/business-strategy/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/rjmurillo/ai-agents/business-strategy"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/business-strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 135 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00104 | $0.02014 |
| Opus 5 | $0.00052 | $0.01007 |
| Sonnet 5 | $0.00021 | $0.00403 |
| Haiku 4.5 | $0.00010 | $0.00201 |
Grade A, and why
business-strategy 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 7d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Business Strategy
The front door to a 14-book business-strategy pack. A founder arrives with a felt problem ("sales are flat", "nobody replies", "I do not know what to build") and no idea which framework applies. This skill names the real problem, routes to the one reference that addresses it, and refuses to guess when the symptom is ambiguous.
Each reference is an original distillation (decision tree, scored checklist, honest limitations, cross-book conflicts, worked example) of one book. They are loaded on demand: read only the one this router points you to.
When to use
Start here whenever the problem is a symptom ("growth stalled") rather than a named method ("run SPIN Selling"). If you already know the framework, skip the router and read its reference directly.
Triggers
| Trigger phrase | Action |
|---|---|
diagnose my business problem |
Walk the decision tree below |
what framework applies |
Walk the decision tree below |
validate demand or find customers |
Start with mom-test; use four-steps only after interview evidence names a repeatable buyer |
price or position this |
Route to monetizing-innovation for price pain, or obviously-awesome for category confusion |
get leads or close deals |
Route to 100m-leads for lead volume, or spin-selling for qualified pipeline stalls |
Decision tree: symptom to reference
Route on the dominant symptom. If two apply, take the earliest funnel stage: an upstream positioning problem usually causes the downstream messaging or pricing problem. Read the named reference, then act.
- You do not know what to build, or whether anyone wants it ->
references/mom-test.md(interview for evidence, not flattery). Follow withreferences/four-steps.mdonly after interviews identify a repeatable buyer but you still lack first-customer motion. - You can build it but have not proven demand ->
references/lean-startup.md(Build-Measure-Learn, smallest MVP that tests the riskiest assumption). - You cannot describe who the product is for, or prospects say "interesting" but do not act ->
references/obviously-awesome.md(positioning and category choice). - You are entering a crowded market and need a wedge ->
references/crossing-the-chasm.md(beachhead). Follow withreferences/blue-ocean-strategy.mdonly when no beachhead can produce a defensible category position. - People want it but balk at the price, or you are guessing the number ->
references/monetizing-innovation.md(price before you build, willingness-to-pay). - The offer itself feels weak ->
references/100m-offers.md(stack value so the price feels trivial). - Traffic is fine but no leads ->
references/100m-leads.md(lead generation), and re-check messaging. - The words on the page fall flat ->
references/storybrand.md(make the customer the hero). Follow withreferences/made-to-stick.mdonly when the message is clear but not remembered or repeated. - Leads stall in the pipeline, or you lose at the close ->
references/spin-selling.md(situation, problem, implication, need-payoff). Follow withreferences/influence.mdonly when discovery is sound but decision dynamics still block action. - You picked product-market fit but have no growth channel ->
references/traction.md(test 19 channels, find the one that works).
What ships with it
15 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/100m-leads.md 6.4 KB
- references/100m-offers.md 7.0 KB
- references/blue-ocean-strategy.md 7.3 KB
- references/crossing-the-chasm.md 6.2 KB
- references/four-steps.md 6.4 KB
- references/influence.md 6.3 KB
- references/lean-startup.md 6.7 KB
- references/made-to-stick.md 7.0 KB
- references/mom-test.md 6.4 KB
- references/monetizing-innovation.md 6.2 KB
- references/obviously-awesome.md 7.4 KB
- references/spin-selling.md 5.9 KB
- references/storybrand.md 5.8 KB
- references/traction.md 7.4 KB
- tests/test_business_strategy_pack.py 4.1 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.
- 7d ago First seen · 137 lines · 104 tokens per session scan A 367a3f83f1a5
business-strategy is a skill published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 104 tokens to every session and 2,014 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 2026-09-03.
Other skills, from other repositories
ci-cd
A guide for designing automated build and delivery workflows with GitHub Actions. These workflows can run checks such as tests, code-quality scans, coverage checks, and builds when code is pushed or a pull request is opened.
openclaw-control
A control interface for the OpenClaw AI assistant, covering messages, status checks, settings, and skill installation.
repository-readiness-eval
Evaluate a repository's readiness for AI-assisted development across 4 axes: code understanding, dependency restore, build success, and test execution. Use when onboarding to a new repo, assessing CI readiness, or validating that an AI agent can work effectively in a codebase.
deploy
Gated CI/CD pipeline management for GitHub Actions and GitLab CI, plus configuration review for other providers when their authenticated tooling is available. Use to set up or fix CI/CD.
loop-triage
Triage recent CI failures, open issues, and recent commits into a prioritized, actionable picture. Reads the prior STATE.md as memory and rewrites it. The maker half of the loop.
ci-triage
How to find out why a GitHub Actions run failed, and how to tell a real failure from a flake or an infrastructure problem. Use when a check is red, a workflow is stuck, or a run needs re-running.