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 cmj-hub/claude-psp --skill psp-onboardinggit clone --depth 1 https://github.com/cmj-hub/claude-pspWrote 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/cmj-hub/claude-psp/psp-onboarding)<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.
<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>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 | $0.00092 | $0.01383 |
| Opus 5 | $0.00046 | $0.00691 |
| Sonnet 5 | $0.00018 | $0.00277 |
| Haiku 4.5 | $0.00009 | $0.00138 |
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.
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.
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.
- 2d ago Changed 912b48b0e0a2
- 11d ago First seen · 175 lines · 92 tokens per session scan A 722038387996
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.
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.
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.
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.…
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…
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.
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.