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 linkedin-engagement-handlergit 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/linkedin-engagement-handler)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/linkedin-engagement-handler"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/linkedin-engagement-handler/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/linkedin-engagement-handler"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/linkedin-engagement-handler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 102 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00098 | $0.02174 |
| Opus 5 | $0.00049 | $0.01087 |
| Sonnet 5 | $0.00020 | $0.00435 |
| Haiku 4.5 | $0.00010 | $0.00217 |
Grade A, and why
linkedin-engagement-handler 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Template placeholders
Replace every {{...}} before enabling. See the setup checklist reference for the full setup list.
{{PROFILE_OWNER}}— Team member whose LinkedIn posts are monitored{{INTERNAL_DOMAINS}}— Your company domain(s){{TEAM_MEMBERS}}— First names / known aliases of your team (engagement from them is ignored){{CRM}}— Your CRM (e.g. HubSpot){{ENGAGEMENT_CHANNEL}}— Slack channel for high-value engagement alerts{{CRM_HYGIENE_SKILL}}— Sub-skill reference: how to create/update companies & contacts in your CRM{{LEAD_SCORING_SKILL}}— Sub-skill reference: lead scoring & qualification methodology{{ALERT_FORMAT_SKILL}}— Sub-skill reference: your alert formatting skill (optional — inline the format if you don't have one){{HIGH_ACV_TAG}}— Workspace tag marking high-ACV-potential accounts{{SELF_SERVE_THRESHOLD}}— Company size below which accounts are self-serve (default: fewer than 30 employees){{ALERT_TIERS}}— Tiers that always alert on first touch (default: Gold, Diamond)
Signal type — read first
Check the event type in the webhook payload before processing:
- New comment → full treatment (everything below).
- New reaction (like) → light touch only: log to {{CRM}} + account memory, then stop. No connection request. No Slack alert. Exception: if the company is tagged {{ALERT_TIERS}}, or this is a repeated engagement (2+ interactions), apply the full treatment.
Comments and reactions are deliberately separate lanes: a comment is an opinion someone attached their name to; a lone like is awareness at best — volume is far higher and signal far lower.
Engagement Process
For Every ICP Lead/Agency Interaction
When someone from an ICP company or relevant agency comments on or likes {{PROFILE_OWNER}}'s post, AND they match a relevant persona:
Relevant personas (tune to your ICP's buying committee):
- Sales Leader (CRO, SVP Sales, VP Sales, Head of Sales, Director of Sales)
- Growth Lead (Head of Growth, Director of Growth, VP Growth, or senior marketing leader)
- CEO (for companies in your core geographic/vertical segment)
- Agency Owner (for agencies in your space)
- GTM Engineer (GTM Engineer, Revenue Engineer, Marketing Engineer, Sales Engineer focused on GTM infrastructure)
- RevOps Lead, Head of Demand Gen, CMO
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +32 lines · +22 tokens per session 860fee601b2f
- 12d ago First seen · 159 lines · 76 tokens per session scan A cf5c588b2921
linkedin-engagement-handler is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed 2d ago), licensed MIT. It adds 98 tokens to every session and 2,174 once invoked, about $0.0005 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 2026-08-30.
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.