psp-construct

psp-construct is a skill for Claude Code from cmj-hub/claude-psp. It costs 67 tokens per session (1,034 once invoked), scanned A, original, MIT.

A guided process for creating a Pain Signal Profile, a document that links public company events to the operational problems that may drive a purchase.

In plain words
What is it for?
Use it to build profiles for a narrowly defined business segment from signals such as hiring, funding, product launches, leadership changes, or new public content.
Why use it?
It helps turn broad market research into a specific description of who has the problem, what signal reveals it, when it matters, and the words that audience uses.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the psp plugin — 5 skills shipped together

Good fit Use it to build profiles for a narrowly defined business segment from signals such as hiring, funding, product launches, leadership changes, or new public content.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/cmj-hub/claude-psp/psp-construct"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-psp/psp-construct.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,034 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 $0.00067 $0.01034
Opus 5 $0.00034 $0.00517
Sonnet 5 $0.00013 $0.00207
Haiku 4.5 $0.00007 $0.00103

Measured yesterday against content hash 30aca08829db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

psp-construct 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 yesterday.

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-construct/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PSP Construct — sub-skill

Loaded by psp when the user wants to build a complete PSP for a specific ICP segment.

Activation

The main psp skill routes here on:

  • "Build a PSP for..."
  • "Construct a Pain Signal Profile for..."
  • "Walk me through a PSP for..."

Workflow

Step 1 — Lock the ICP segment

Ask the user to be specific. Push back on broad ICPs.

"B2B SaaS" is too broad. Try one of these shapes:

  • "Series-B SaaS, $20-50M ARR, with a PLG motion"
  • "DevTools companies with >50 engineers and an OSS community"
  • "Bootstrapped agencies, 5-15 employees, productized service"

Which segment?

Step 2 — Hunt signals

For the segment, surface 5-10 candidate signals. Patterns:

  • Hiring signals: Specific role open ≤30 days
  • Funding signals: Round announced ≤30 days
  • Product signals: New tier / launch / pricing change ≤45 days
  • Leadership signals: New CMO / CRO / CFO / Head-of-X ≤60 days
  • Content signals: Recent podcast / panel / public talk on the topic
  • Pivot signals: Website hero / positioning change ≤14 days

If WebFetch is available, demo-pull recent LinkedIn job posts or recent funding news for one example company in the segment.

Step 3 — Map signal → pain for top 3

For each of the top 3 signals, ask: "If this happened, what is the operator at that company feeling at 11am on Tuesday?"

Validate each pain:

  • Specific operational moment (not abstract)
  • Phrased as what they feel, not what you sell
  • Uses their language (not category jargon)

Step 4 — Anchor timing

For each pain, identify the 90-day trigger:

  • New exec → 90-day plan in motion
  • Budget cycle → planning/fiscal-new-year window
  • Obvious failure → quarter miss, churn spike, launch flop

If no trigger, the PSP isn't time-anchored — push back.

Step 5 — Identify felt-pain role

Who in the org feels the pain at 11am Tuesday?

Note: this is often a layer below the buying authority. The demand-gen lead feels pipeline-gap pain; the CMO authorizes the spend. Outreach hits the felt-pain role.

Read the full file on GitHub · 138 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. yesterday Changed · -1 lines 30aca08829db
  2. 9d ago First seen · 139 lines · 67 tokens per session scan A b10fcddce938

Subscribe to this mod's changes

psp-construct is a skill published in the GitHub repository cmj-hub/claude-psp (2 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 1,034 once invoked, about $0.0003 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