psp-onboarding

psp-onboarding is a skill for Claude Code from cmj-hub/claude-psp. It costs 92 tokens per session (1,383 once invoked), scanned A, original, MIT.

A first-run setup guide for the PSP skill pack, which creates project-specific guidance about your target customers and their language. ICP means the specific kind of customer a product is meant for.

In plain words
What is it for?
Use it when setting up PSP for the first time or when its brand configuration is missing or needs refreshing.
Why use it?
It prevents the skill pack from producing generic business writing by requiring details about the customers, their vocabulary, past examples, and boundaries.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions AGENTS.md.

Part of the psp plugin — 5 skills shipped together

Good fit Use it when setting up PSP for the first time or when its brand configuration is missing or needs refreshing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cmj-hub/claude-psp/psp-onboarding
Install

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.

Any agent
npx skills add cmj-hub/claude-psp --skill psp-onboarding
Clone the repo
git clone --depth 1 https://github.com/cmj-hub/claude-psp

Made for: Claude Code.

Or install psp, the plugin that ships this one along with the rest of its 5 skills.

Wrote 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.

agentmods badge for psp-onboarding

README.md
[![agentmods](https://agentmods.dev/badge/skills/cmj-hub/claude-psp/psp-onboarding/github.svg)](https://agentmods.dev/skills/cmj-hub/claude-psp/psp-onboarding)
Your own site
<a href="https://agentmods.dev/skills/cmj-hub/claude-psp/psp-onboarding"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-psp/psp-onboarding/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.

agentmods 80×15 button for psp-onboarding

Your own site · 80×15
<a href="https://agentmods.dev/skills/cmj-hub/claude-psp/psp-onboarding"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-psp/psp-onboarding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,383 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00092 $0.01383
Opus 5 $0.00046 $0.00691
Sonnet 5 $0.00018 $0.00277
Haiku 4.5 $0.00009 $0.00138

Measured 2d ago against content hash 912b48b0e0a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

psp-onboarding 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 2d 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.

skills/psp-onboarding/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PSP Onboarding — first-run setup

Walks the operator through ~15 minutes of setup that makes every downstream PSP 10x more useful than generic framework prose.

Activation

Loaded automatically by the psp orchestrator when brand-config.json or SOUL.md is missing from the project root.

Also user-invocable: "Set up PSP brand config", "PSP onboarding", "Configure PSP".

Why this exists

A generic PSP that says "Series-B SaaS feels pipeline pressure" is worse than no PSP — it produces outreach that everyone else is also producing. The 5-component PSP framework only generates real differentiation when paired with:

  • Your ICP precision (segment, exclusion, motion)
  • Your buyer's actual vocabulary (sourced from real writing, not invented)
  • Your stories (signal-to-pain mappings you've seen succeed or fail before)
  • Your won't-chase boundaries

Workflow

Step 0 — Detect prior state

Check for existing brand-config.json + SOUL.md. If both exist, ask: "Refresh, or skip?" If one exists, fill the gap.

Step 1 — ICP precision

First, ICP. Be specific — "B2B SaaS" is too broad.

Tell me in one batch:
1. The 1-sentence segment (stage / size / motion / region)
2. The size range ($M ARR)
3. The motion (PLG / sales-led / hybrid)
4. The 3-5 exclusion criteria (who you don't sell to)

If your ICP is fuzzy, that's a finding — outreach against a fuzzy ICP
will be fuzzy. We can use placeholders for now and flag them for refresh
after 100 sends.

Save to brand-config.icp.

Step 2 — Primary PSP draft

Now your primary PSP. Five components:

1. SIGNAL — what's a public, recent, verifiable thing your buyer does
   that implies the pain? (job post, funding round, leadership change,
   product launch, pricing change)
2. PAIN — what's the felt operational reality at 11am Tuesday when
   that signal is present? In their language, not yours.
3. TIMING TRIGGER — which 90-day window makes the pain acute now:
   new-exec / budget-cycle / obvious-failure?
4. FELT-PAIN ROLE — who at the buyer feels it most? (Often a layer
   below the buying authority.)
5. VOCABULARY — 4-8 phrases the buyer uses in private about this. If
   you don't know yet, that's step 3.

Read the full file on GitHub · 175 lines

Changes

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.

  1. 2d ago Changed 912b48b0e0a2
  2. 11d ago First seen · 175 lines · 92 tokens per session scan A 722038387996

Subscribe to this mod's changes

psp-onboarding is a skill published in the GitHub repository cmj-hub/claude-psp (2 stars, last pushed 2d ago), licensed MIT. It adds 92 tokens to every session and 1,383 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 2026-08-31.

Related

Other skills, from other repositories

afrexai-lead-hunter

Enterprise-grade B2B lead generation, enrichment, scoring, and outreach sequencing for AI agents. Find ideal prospects, enrich with verified data, score against your ICP, and generate personalized outreach — all autonomously.

LeoYeAI/openclaw-master-skills · 50 tokens

go-to-market-playbook

A reusable Go-to-Market strategy template for both B2B and B2C launches. Covers positioning, messaging, ICP definition, channel selection, and competitive analysis frameworks. By @WeiYipei.

Gingiris-1031/gingiris-skills · 48 tokens

evp

Early Value Proposition (EVP) generator for B2B operators. Uses the Eugene Schwartz awareness model (unaware, problem-aware, solution-aware, product-aware, most-aware) to produce a sharp, 22-word EVP for each awareness tier — plus a structured 3-tier EVP brief documenting the audience, pain, EVP, and proof per tier.…

cmj-hub/claude-evp · 174 tokens

evp-brief

Build a structured 3-tier EVP brief — Tier 2 (problem-aware), Tier 3 (solution-aware), Tier 4 (product-aware) — side-by-side with audience, pain, EVP variants, and proof per tier. Becomes the single source of truth your hero, ads, cold email, and pricing-page pull from. Loaded by the main evp skill when the user wants…

cmj-hub/claude-evp · 88 tokens

evp-craft

Generate 3 EVP variants for a single Schwartz awareness tier. Each variant follows the 22-word shape and explores a different emphasis (outcome / tradeoff / ICP). Loaded by the main evp skill when the user wants to craft EVPs for a specific tier.

cmj-hub/claude-evp · 59 tokens

evp-kickoff

Adaptive router for the EVP skill pack. Detects state (brand-config? SOUL? primary EVP locked per tier? competitors named? proofs reservoir?) and picks the next-best step. Loaded by the main evp skill on bare invocation.

cmj-hub/claude-evp · 54 tokens