YALC-the-GTM-operating-system: Skill for Claude Code

.claude/skills/predictleads-signals/SKILL.md

predictleads-signals is a skill for Claude Code from Othmane-Khadri/YALC-the-GTM-operating-system. It costs 74 tokens per session (822 once invoked), scanned A, original, MIT.

A single-company lookup for PredictLeads, a service that reports business signals such as hiring, funding, technology use, news, and similar companies. It also reads previously saved results from a local database.

In plain words
What is it for?
Use it to check what is happening at a company, support lead qualification, review hiring or funding activity, inspect its technology stack, or read saved signals offline.
Why use it?
It gives quick context about one company without repeatedly requesting the same data. Cached results can be read without making another service request.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Othmane-Khadri/YALC-the-GTM-operating-system's own configuration. It tells Claude Code how to work on YALC-the-GTM-operating-system itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything YALC-the-GTM-operating-system configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Othmane-Khadri/YALC-the-GTM-operating-system. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Othmane-Khadri/YALC-the-GTM-operating-system/main/.claude/skills/predictleads-signals/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Othmane-Khadri/YALC-the-GTM-operating-system

Made for: Claude Code.

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 predictleads-signals

README.md
[![agentmods](https://agentmods.dev/badge/skills/othmane-khadri/yalc-the-gtm-operating-system/predictleads-signals/github.svg)](https://agentmods.dev/skills/othmane-khadri/yalc-the-gtm-operating-system/predictleads-signals)
Your own site
<a href="https://agentmods.dev/skills/othmane-khadri/yalc-the-gtm-operating-system/predictleads-signals"><img src="https://agentmods.dev/badge/skills/othmane-khadri/yalc-the-gtm-operating-system/predictleads-signals/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 predictleads-signals

Your own site · 80×15
<a href="https://agentmods.dev/skills/othmane-khadri/yalc-the-gtm-operating-system/predictleads-signals"><img src="https://agentmods.dev/badge/skills/othmane-khadri/yalc-the-gtm-operating-system/predictleads-signals.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 822 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 5 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 23
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 26
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 29
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 32
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 33
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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 $0.00074 $0.00822
Opus 5 $0.00037 $0.00411
Sonnet 5 $0.00015 $0.00164
Haiku 4.5 $0.00007 $0.00082

Measured 13d ago against content hash 3bbc788143ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

predictleads-signals scanned grade A with 1 finding 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 13d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Live PredictLeads quota: hit `/api_subscription` once via curl to see remaining credits. Or just run `signals:fetch` and the output prints cache hit / +N signals per type.
.claude/skills/predictleads-signals/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PredictLeads Signals (single company)

Pulls and reads company-level intent signals from PredictLeads: job openings, financing events, technologies, news events, similar companies. Stored in local SQLite (company_signals table) with a 7-day TTL cache so repeat lookups within the week cost zero credits.

When to use

  • Quick lookup before an outbound message: "what's happening at hubspot.com?"
  • Adding signal context to a single lead during qualification
  • Reading cached signals offline (no API call) via signals:show
  • Sanity-checking a company's marketing maturity (tech stack, hiring pace)

Don't use when: enriching a list of >5 companies (use predictleads-lookalikes for discovery, or the bulk signals:enrich --result-set); building a campaign (use prospect-discovery-pipeline).

Quick reference

# Pull all 4 signal types for one company (1 credit per type = 4 credits)
npx tsx src/cli/index.ts signals:fetch --domain hubspot.com

# Restrict to specific types (saves credits)
npx tsx src/cli/index.ts signals:fetch --domain hubspot.com --types jobs,funding

# Force re-fetch even if cached within TTL
npx tsx src/cli/index.ts signals:fetch --domain hubspot.com --no-cache

# Read cached signals locally (no API call, free)
npx tsx src/cli/index.ts signals:show --domain hubspot.com --limit 20
npx tsx src/cli/index.ts signals:show --domain hubspot.com --type news

Cost

Operation Credits
signals:fetch (4 types, default) 4
signals:fetch --types jobs,funding 2
signals:fetch re-run within 7 days 0 (cache hit)
signals:show 0 (local read)

Live PredictLeads quota: hit /api_subscription once via curl to see remaining credits. Or just run signals:fetch and the output prints cache hit / +N signals per type.

Signal types and aliases

jobs (job_opening), funding (financing), tech (technology), news, similar (similar_company)

Common pitfalls

  • Domain format: pass the bare domain (hubspot.com), not https://hubspot.com or www.hubspot.com. The service tolerates either but URLs in payloads are cleaner.
  • News and tech rows look empty in signals:show: payloads use summary (news) and resolved relationships (tech) instead of title. The display already falls through to summary. If you see blanks, check the raw payload via sqlite3 ~/.gtm-os/gtm-os.db "SELECT payload FROM company_signals WHERE domain='X' LIMIT 1".
  • Cache invalidation: 7 days is the default TTL. Pass --no-cache to force a refresh. Caching is per (domain, signal_type), so refreshing news doesn't re-pull jobs.

Read the full file on GitHub · 60 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. 13d ago First seen · 60 lines · 74 tokens per session scan A 3bbc788143ec

Subscribe to this mod's changes

predictleads-signals is a skill published in the GitHub repository Othmane-Khadri/YALC-the-GTM-operating-system (301 stars, last pushed 23d ago), licensed MIT. It adds 74 tokens to every session and 822 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.