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-kickoffgit 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-kickoff)<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.
<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>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 | $0.00064 | $0.00864 |
| Opus 5 | $0.00032 | $0.00432 |
| Sonnet 5 | $0.00013 | $0.00173 |
| Haiku 4.5 | $0.00006 | $0.00086 |
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.
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)
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 ffa6b8f99d3e
- 11d ago First seen · 92 lines · 64 tokens per session scan A f60f2fe5f1e1
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.
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.