psp-signal-hunt

psp-signal-hunt is a skill for Claude Code from cmj-hub/claude-psp. It costs 73 tokens per session (836 once invoked), scanned A, original, MIT.

A research-planning skill for identifying public, recent, and verifiable signs that a type of potential customer may be ready for outreach. ICP means the ideal customer profile.

In plain words
What is it for?
Use it to propose five to ten signals across hiring, funding, leadership, products, company pivots, and public content, along with practical sources and a tracking schedule.
Why use it?
It turns a broad audience description into specific signals to monitor, instead of relying on guesswork about who might need a product.

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 propose five to ten signals across hiring, funding, leadership, products, company pivots, and public content, along with practical sources and a tracking schedule.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/cmj-hub/claude-psp/psp-signal-hunt"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-psp/psp-signal-hunt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 836 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 $0.00073 $0.00836
Opus 5 $0.00036 $0.00418
Sonnet 5 $0.00015 $0.00167
Haiku 4.5 $0.00007 $0.00084

Measured 3d ago against content hash e5adfc57c102, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

psp-signal-hunt 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 3d 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-signal-hunt/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PSP Signal Hunt — sub-skill

Loaded by psp when the user wants to identify what signals to track for a specific ICP segment.

Activation

The main psp skill routes here on:

  • "What signals should we hunt for "
  • "Find signals for "
  • "Signal hunt"

Signal taxonomy

The skill produces signal candidates across 6 categories:

Category Examples
Hiring Specific role open ≤30 days; team size jump; first-of-kind hire (first SDR, first VP)
Funding Round announced ≤30 days; secondary; bridge; ARR milestone
Leadership New C-level / VP ≤60 days; departure; board change
Product New tier / pricing change / feature launch / public roadmap ≤45 days
Pivot Website hero rewrite; positioning shift; rebrand; new ICP language
Content Podcast / panel / public talk on the relevant pain ≤30 days

Workflow

1. Take the ICP segment

The user provides a specific ICP (e.g. "Series-B SaaS, $20-50M ARR, PLG motion"). If they're vague, ask for precision before continuing.

2. Generate 5-10 candidate signals

For each candidate, output:

  • Signal type (from the 6 categories)
  • What to look for (specific shape — e.g. "Demand Gen Lead role posted ≤14 days")
  • Where to find it (LinkedIn / Crunchbase / RSS / podcast feeds / their own blog)
  • Cadence (daily / weekly / event-driven)
  • Why this signal implies operational pain for this ICP

3. Rank by hunting feasibility

Rank the 5-10 candidates by:

  • Volume: how many target companies show this signal monthly
  • Specificity: how directly it implies actionable pain
  • Effort: how hard to operationalize the hunt

4. Output

# Signal hunt — <ICP segment>

| # | Signal | Where | Cadence | Pain implied | Volume |
|---|---|---|---|---|---|
| 1 | Demand Gen Lead role posted ≤14d | LinkedIn job search + RSS | Daily | Pipeline gap | ~15-30/mo |
| 2 | Series B announced ≤30d | Crunchbase API + CB Insights newsletter | Weekly | 3x revenue mandate | ~5-10/mo |
| 3 | New CMO ≤60d | LinkedIn search + The Org | Weekly | 90-day GTM stack review | ~3-8/mo |
| 4 | ... | ... | ... | ... | ... |

## Recommended hunt stack
1. **Daily**: LinkedIn job posts (manual or via Phantombuster)
2. **Weekly**: Crunchbase + The Org
3. **Event-driven**: Podcast RSS for relevant shows

## Operational notes
- Capture signal date so freshness is enforced
- Tag each signal with the implied pain at capture time
- Stale signals (>45 days for hiring, >30 days for funding) drop from outreach queue

Read the full file on GitHub · 88 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. 3d ago Changed e5adfc57c102
  2. 12d ago First seen · 88 lines · 73 tokens per session scan A 966381555762

Subscribe to this mod's changes

psp-signal-hunt is a skill published in the GitHub repository cmj-hub/claude-psp (2 stars, last pushed 3d ago), licensed MIT. It adds 73 tokens to every session and 836 once invoked, about $0.0004 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