psp

psp is a skill for Claude Code from cmj-hub/claude-psp. It costs 155 tokens per session (1,895 once invoked), scanned A, original, MIT.

A framework for turning public business signals into a clear picture of an organisation's operational pain. Signals can include hiring, funding, leadership changes, product launches, or pricing changes.

In plain words
What is it for?
It helps research target companies, identify relevant business signals, describe the resulting pain and timing, and shape outreach or sales messaging.
Why use it?
It connects observable events to why a potential buyer may need help now, instead of relying only on broad customer profiles.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the psp plugin — 5 skills shipped together

Good fit It helps research target companies, identify relevant business signals, describe the resulting pain and timing, and shape outreach or sales messaging.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/cmj-hub/claude-psp/psp"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-psp/psp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,895 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 $0.00155 $0.01895
Opus 5 $0.00077 $0.00948
Sonnet 5 $0.00031 $0.00379
Haiku 4.5 $0.00015 $0.00189

Measured 2d ago against content hash f680ea1b5b3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

psp 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.

psp/SKILL.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PSP — Pain Signal Profile Builder

A Pain Signal Profile is the link from a public signal (something the prospect verifiably did) to the felt operational pain that signal implies. It's the foundation underneath cold email, outbound audits, EVPs, content strategy, and sales conversations in the JMC framework.

Quick reference

Slash What it does
/psp Interactive — build a PSP from scratch with the operator
/psp construct <ICP> Walk through PSP construction for a specific ICP segment
/psp signal-hunt <ICP> Surface 5-10 public signals worth hunting for an ICP
/psp validate <PSP> Stress-test a draft PSP against the framework

The core stance

A PSP is not an ICP, persona, or demographic. Those describe who the buyer is. A PSP describes:

  1. What the buyer just did (signal — public, recent, verifiable)
  2. What that signal implies about their operational reality (pain)
  3. Why now the pain is acute (timing)
  4. Who feels the pain most within the company (role)
  5. What language they use about it internally (vocabulary)

If you can't fill in all five, you don't have a PSP yet.

The framework

Signal      →  Pain          →  Timing       →  Role          →  Vocabulary
(verifiable    (operational    (why now is    (who feels it    (their words,
 thing they    consequence)    acute)          most)            not yours)
 did)

Component 1: Signal

A signal is something the prospect (or their company) did publicly, recently, and verifiably.

Good signals:

  • Just posted a job for <role> on LinkedIn (≤30 days)
  • Just announced funding (Series A/B/C, ≤30 days)
  • Just shipped a feature / product / pricing change (≤45 days)
  • Just hired / promoted a relevant exec (≤30 days)
  • Just changed website positioning or hero (≤14 days)
  • Just appeared on a relevant podcast / conference / panel
  • Just published a content piece on the topic

Not signals:

  • "Series B company" (state, not action)
  • "VP of Marketing" (role, not action)
  • "Growing fast" (vague, not verifiable)

Read the full file on GitHub · 218 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 · -9 lines f680ea1b5b3e
  2. 10d ago First seen · 227 lines · 155 tokens per session scan A 6487f5510255

Subscribe to this mod's changes

psp is a skill published in the GitHub repository cmj-hub/claude-psp (2 stars, last pushed 2d ago), licensed MIT. It adds 155 tokens to every session and 1,895 once invoked, about $0.0008 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