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 SZoloth/skill-pack --skill b2b-expert-advisorgit clone --depth 1 https://github.com/SZoloth/skill-packWrote 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/szoloth/skill-pack/b2b-expert-advisor)<a href="https://agentmods.dev/skills/szoloth/skill-pack/b2b-expert-advisor"><img src="https://agentmods.dev/badge/skills/szoloth/skill-pack/b2b-expert-advisor.svg" alt="Measured on agentmods" 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 | $0.00101 | $0.01000 |
| Opus 5 | $0.00051 | $0.00500 |
| Sonnet 5 | $0.00020 | $0.00200 |
| Haiku 4.5 | $0.00010 | $0.00100 |
Grade A, and why
b2b-expert-advisor 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
B2B expert advisor
Overview
Provide B2B startup strategy advice grounded in specific frameworks and data from Lenny Rachitsky's 7-part B2B series and April Dunford's positioning methodology. All guidance references concrete examples, benchmarks, and patterns from these sources rather than generic advice.
Source library
The knowledge base lives in the resources/ directory alongside this file. Load only the files relevant to the user's question — never load all 9 at once.
Topic routing
| User question involves... | File to load |
|---|---|
| What successful B2B startups have in common, patterns, benchmarks | resources/successful-b2b-startups.md |
| Validating a B2B idea, testing demand, early signals | resources/validate-b2b-startup.md |
| ICP, ideal customer profile, who to sell to first | resources/identify-ideal-customer.md |
| First 10 customers, early sales, landing first deals | resources/win-first-10-b2b-customers.md |
| Product-market fit, PMF signals, when you have PMF | resources/finding-product-market-fit.md |
| Hiring, early team, first hires, team building | resources/hiring-early-team-b2b.md |
| Growth engine, scaling, channels, B2B growth | resources/scaling-b2b-growth-engine.md |
| Positioning (fundamentals), April Dunford, category design | resources/positioning.md |
| Advanced positioning, repositioning, positioning pitfalls | resources/advanced-b2b-positioning.md |
For questions spanning multiple topics (e.g., "how do I go from idea to first customers"), load 2-3 relevant files max.
Workflow
- Route the question — Match the user's question to 1-3 files from the topic routing table above.
- Load source material — Read the matched files from
resources/. - Extract relevant frameworks — Pull the specific frameworks, examples, benchmarks, or decision criteria that apply.
- Advise with citations — Give concrete guidance. Cite the source article and specific frameworks by name (e.g., "April Dunford's 5-step positioning process" or "Lenny's B2B validation ladder").
- Apply to user's context — When the user shares details about their specific product or market, cross-reference the frameworks against their situation.
What ships with it
9 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.
- resources/advanced-b2b-positioning.md 21 KB
- resources/finding-product-market-fit.md 31 KB
- resources/hiring-early-team-b2b.md 19 KB
- resources/identify-ideal-customer.md 15 KB
- resources/positioning.md 27 KB
- resources/scaling-b2b-growth-engine.md 15 KB
- resources/successful-b2b-startups.md 54 KB
- resources/validate-b2b-startup.md 20 KB
- resources/win-first-10-b2b-customers.md 40 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.
- 7d ago First seen · 72 lines · 101 tokens per session scan A f0de64b35e34
b2b-expert-advisor is a skill published in the GitHub repository SZoloth/skill-pack (14 stars, last pushed 5mo ago), licensed MIT. It adds 101 tokens to every session and 1,000 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
claudeshrink
Automatically compress large natural text or log files before processing. Trigger when the user pastes massive text blobs, or asks to analyze a large file (logs, docs, transcripts), or provides a prompt that is too large for the context window. DO NOT trigger on source code files or structural data (JSON, XML).
self-improve
Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new skills). Use when the user asks to "self-improve", "distill this session", "distill past sessions", "sweep past…
smoke-test
Launch the app and hands-on verify that it works by interacting with it. Falls back to an existing integration test suite when there is no interactive surface in scope. Use when the user asks to "smoke test", "test it manually", "verify it works", "try it out", "run a smoke test", "check it in the browser", or "does…
draft-plan
Produce an implementation plan at .turbo/plans/ .md. Use when the user asks to "draft a plan", "draft the plan", "write an implementation plan", "plan this change", "create an implementation plan", or needs a first-draft plan file before refinement.
resolve-pr-comments
Evaluate, fix, answer, and reply to GitHub pull request review comments and conversation comments. Handles both change requests (fix or skip) and reviewer questions (explain using reasoning recalled from past Claude Code transcripts). Use when the user asks to "resolve PR comments", "fix review comments", "address PR…
consult-codex
Multi-turn consultation with Codex CLI for second opinions, brainstorming, or collaborative problem-solving. Use when the user asks to "consult codex", "ask codex", "get codex's opinion", "brainstorm with codex", "discuss with codex", or "chat with codex".