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 swan-gtm/gtm-skills --skill territory-signal-digestgit clone --depth 1 https://github.com/swan-gtm/gtm-skillsWrote 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/swan-gtm/gtm-skills/territory-signal-digest)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/territory-signal-digest"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/territory-signal-digest/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/swan-gtm/gtm-skills/territory-signal-digest"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/territory-signal-digest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00071 | $0.01087 |
| Opus 5 | $0.00036 | $0.00544 |
| Sonnet 5 | $0.00014 | $0.00217 |
| Haiku 4.5 | $0.00007 | $0.00109 |
Grade A, and why
territory-signal-digest 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 9d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run a weekly signal sweep across every account in a territory. Rank accounts by signal strength. Surface what moved since last week. Return a brief the rep can act on before their first call.
Input
The user will provide via $ARGUMENTS:
- Account list (required) — a list of company names, domains, or Lusha company IDs. Paste inline or reference a saved list.
- Lookback window (optional) — how far back to pull signals. Default: 7 days for weekly digest. Accept: 30 days, 90 days.
- Signal focus (optional) — which signal types to prioritize.
Default: all. Options:
- Role changes (promotions, job changes, departures)
- Hiring surges (open roles in target functions)
- Funding (rounds, investment announcements)
- Intent (buying signals on your category)
- News (product launches, M&A, leadership moves)
If account list is missing, ask once. If declined, return an error — the skill cannot run without a list of accounts.
Workflow
-
Anchor on the digest purpose. Read the lookback window and signal focus from $ARGUMENTS. Default to 7-day lookback and all signal types if not supplied. State the parameters at the top of the output so the reader knows what the digest covers.
-
Resolve accounts via Lusha. For each account in the list:
- If a Lusha company ID is supplied, use it directly.
- Otherwise resolve via companies_search using the name or domain.
- Flag any accounts that could not be resolved and skip them. List unresolved accounts at the end of the output.
-
Pull signals in parallel. For each resolved account, run these calls concurrently:
- Buying signals: intent topics, signal score 60+, ranked by score. Lookback window as specified.
- News and scoops: last 7 days (or specified window). Leadership moves, funding, product launches, M&A, layoffs.
- Hiring signals: open roles in target functions posted in the lookback window.
- Contact changes: promotions, job changes, departures for key contacts at the account.
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.
- 9d ago First seen · 148 lines · 71 tokens per session scan A b2ca28ecf8ef
territory-signal-digest is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed 2d ago), licensed MIT. It adds 71 tokens to every session and 1,087 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 2026-09-03.
Other skills, from other repositories
intent-signal-monitor
Track buying signals across multiple channels and score them by strength.
meeting-debrief
Analyzes sales meetings for buying signals, red flags, and next steps with a deal scorecard.
huashu-bento-insight
OpenDesign vs closed cloud design tools: a side-by-side displacement case on control, cost (BYOK), and lock-in. Built as a decision-grade B2B sales deck for evaluation committee.
html-ppt-product-launch
OpenDesign Teams: a launch-and-adoption proposal for a mid-market design team weighing a switch from closed cloud tools. Built as a decision-grade B2B sales deck for design team lead, IT.
signals-dart
Advanced reactive state primitives, collections, mixins, and utilities of signalscore.
signals-migration-6-to-7
Detailed guidelines, patterns, and rules for migrating codebases from signals.dart version 6.x to version 7.x.