psp-kickoff

psp-kickoff is a skill for Claude Code from cmj-hub/claude-psp. It costs 64 tokens per session (864 once invoked), scanned A, original, MIT.

A state-aware guide for Persona-Specific Positioning (PSP), a method for defining who an outreach message is meant for and why it matters to them. It checks your existing PSP work and selects the next step.

In plain words
What is it for?
Use it to find the next action in an outreach-planning process, from initial setup through audience definition, vocabulary gathering, signal research, and updates.
Why use it?
It removes the guesswork from starting or continuing PSP work. You can see whether to set up the basics, define a primary or secondary audience, improve wording, find signals, or refresh older work.

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 find the next action in an outreach-planning process, from initial setup through audience definition, vocabulary gathering, signal research, and updates.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/cmj-hub/claude-psp/psp-kickoff"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-psp/psp-kickoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 864 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 $0.00064 $0.00864
Opus 5 $0.00032 $0.00432
Sonnet 5 $0.00013 $0.00173
Haiku 4.5 $0.00006 $0.00086

Measured 2d ago against content hash ffa6b8f99d3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

psp-kickoff 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-kickoff/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PSP Kickoff — adaptive router

State-aware router for PSP work. Operators don't ship outreach on day 1 — they walk a sequence: ICP precision → primary PSP → vocabulary mining → secondary PSPs → operationalize signal hunting → refresh.

Activation

Loaded by psp on bare invocation, or:

  • "Where do I start with PSPs"
  • "What's next for my PSP work"
  • "I'm new to PSPs"

State detection

state = {
    "has_brand_config":    file_exists("brand-config.json"),
    "has_soul":            file_exists("SOUL.md"),
    "has_primary_psp":     brand_config.psp_drafts.primary and brand_config.psp_drafts.primary.pain != "",
    "has_secondary_psp":   brand_config.psp_drafts.secondary is not None,
    "vocabulary_ok":       len(brand_config.psp_drafts.primary.vocabulary or []) >= 4,
    "signals_sourced":     any value true in brand_config.signal_sources,
    "psp_age_days":        days_since(brand_config.psp_drafts.primary.refreshed_at),
}
State Route to
!has_brand_config OR !has_soul psp-onboarding
has_config AND !has_primary_psp psp-construct (build primary PSP)
has_primary_psp AND !vocabulary_ok "Vocabulary list <4 phrases — let's mine more. Need help?"
vocabulary_ok AND !signals_sourced "Pick signal sources. Run psp signal-hunt."
signals_sourced AND psp_age_days > 90 "PSP last refreshed >90 days ago — re-run onboarding refresh"
signals_sourced AND psp_age_days < 90 "PSP is fresh + operational. Want to build a secondary PSP? Or push downstream into claude-evp + claude-cold-email?"

Welcome flow

> /psp

Welcome. Let's figure out where you are.

[Detected: brand-config.json missing]

You're at step 1 of 6:

1. ⬜ Onboarding — capture ICP + 1 primary PSP draft (15 min)   ← YOU ARE HERE
2. ⬜ Mine 8+ vocabulary phrases from real buyer writing
3. ⬜ Pick signal sources + cadence
4. ⬜ Run first signal hunt → 5-10 candidates
5. ⬜ Build secondary PSP for the next-priority segment
6. ⬜ Plug into claude-evp + claude-cold-email downstream

Step 1 takes ~15 minutes. Ready? (y/n)

Read the full file on GitHub · 92 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 ffa6b8f99d3e
  2. 11d ago First seen · 92 lines · 64 tokens per session scan A f60f2fe5f1e1

Subscribe to this mod's changes

psp-kickoff is a skill published in the GitHub repository cmj-hub/claude-psp (2 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 864 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