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-constructgit 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-construct)<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.
<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>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 | $0.00067 | $0.01034 |
| Opus 5 | $0.00034 | $0.00517 |
| Sonnet 5 | $0.00013 | $0.00207 |
| Haiku 4.5 | $0.00007 | $0.00103 |
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.
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.
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.
- yesterday Changed · -1 lines 30aca08829db
- 9d ago First seen · 139 lines · 67 tokens per session scan A b10fcddce938
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.
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.