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-signal-huntgit 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-signal-hunt)<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.
<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>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 | $0.00073 | $0.00836 |
| Opus 5 | $0.00036 | $0.00418 |
| Sonnet 5 | $0.00015 | $0.00167 |
| Haiku 4.5 | $0.00007 | $0.00084 |
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.
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
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.
- 3d ago Changed e5adfc57c102
- 12d ago First seen · 88 lines · 73 tokens per session scan A 966381555762
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.
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.