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 signal-interpretergit 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/signal-interpreter)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/signal-interpreter"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/signal-interpreter/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/signal-interpreter"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/signal-interpreter.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 | $0.00075 | $0.04465 |
| Opus 5 | $0.00037 | $0.02233 |
| Sonnet 5 | $0.00015 | $0.00893 |
| Haiku 4.5 | $0.00007 | $0.00447 |
Grade A, and why
signal-interpreter 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Signal Interpreter
Pure interpretation layer for GTM signals — returns relevance, meaning, strength, confidence, category, why-now, and open questions. No tier math or memory writes. Runs before your tier-scoring stage.
Template placeholders
{{COMPANY_NAME}}— Your company's name.{{ICP_DOMAIN}}— The operational world your product lives in: the set of activities, asset types, workflows, and regulatory contexts where a prospect's signal becomes relevant to you. Define it as a concrete list, not a category label. E.g., for a digital-asset custody company: digital assets, stablecoins, treasury flows, tokenized assets, crypto/payment infrastructure, wallet governance, custody, compliance, cross-border settlement, and regulated financial services. Write yours with the same specificity — this list powers the Relevance Gate and every strength/confidence judgment below.{{ICP_VOCABULARY}}— The specific operational-complexity vocabulary of your domain, used to phrase business implications. E.g., for the same custody company: wallet governance, transaction policy, treasury movement, custody, compliance workflows, settlement operations, approval flows, key management.
Worked examples throughout use the digital-asset custody domain (the domain this skill was battle-tested in) — substitute your own everywhere.
Purpose
This skill is the interpretation layer between a raw GTM signal and downstream routing. It explains what a signal likely means, why it matters, what should not be assumed, how strong the signal is, and how confident we are.
It is pure interpretation and has no side effects. It does NOT assign tiers, decide actions, choose channels, send alerts, create tasks, or write memory:
- Tier math (tier, boosters, reducers, caps, ACV, accumulation, decay, market modifiers, tier action) -> your tier-scoring stage.
- Routing, alerts, memory writes -> your signal post-processing/routing stage.
- Outreach angle / messaging -> your messaging and lead-routing stages.
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 · 274 lines · 75 tokens per session scan A 2a8f27b491df
signal-interpreter is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed 2d ago), licensed MIT. It adds 75 tokens to every session and 4,465 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
signals-hooks
Comprehensive reactive state hooks for integration with flutterhooks.
signals-dart
Advanced reactive state primitives, collections, mixins, and utilities of signalscore.
signals-flutter
Highly optimized Flutter UI bindings and GPU rendering for reactive signals.
signals-migration-6-to-7
Detailed guidelines, patterns, and rules for migrating codebases from signals.dart version 6.x to version 7.x.
signals-preact-dart
Core reactive programming best practices and primitive definitions for preactsignals in Dart.
signals-lint
Standardized compiler diagnostics, static analysis lints, and automated IDE quick-fixes.