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 post-radargit 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/post-radar)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/post-radar"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/post-radar/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/post-radar"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/post-radar.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 | $0.00033 | $0.01306 |
| Opus 5 | $0.00016 | $0.00653 |
| Sonnet 5 | $0.00007 | $0.00261 |
| Haiku 4.5 | $0.00003 | $0.00131 |
Grade A, and why
post-radar 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
Setup state. Not yet configured for this org. Load the Setup sub-page and walk the user through wiring the LINKEDIN_ENGAGEMENT trigger with the right set of monitored profiles (founder, execs, company page, competitor pages, thought leaders), engagement types, noise filters, and follow-up sequence before running this play. (After setup is performed, rewrite this paragraph via swan-update-skill to describe the current state — monitored profile list, engagement types tracked (comments / reactions / reposts), noise filters applied, sequence wired, success metric, and last-refreshed date — so future runs see the current configuration without re-checking.)
When this fires
A LINKEDIN_ENGAGEMENT trigger lands. Payload includes: the post URL, the post content (or summary), the engager's name + LinkedIn URL, engagement type (comment / reaction / repost), and the comment text if it's a comment.
Speed matters. Replying within 24 hours converts much better than 72+ hours.
Step 1 — Filter the noise
Not every engagement is worth acting on. Quick filters:
- Generic emoji-only reactions → low signal, skip unless they're a high-value account
- One-word comments ("Love this!", "100%") → skip unless from an ICP-fit person
- Competitors and vendors → never engage as a sales motion; flag for awareness only
- Existing customers → route to CSM, not to outbound
- Internal employees → skip
Set a minimum threshold: comments ≥ ~15 words, or any engagement from a known ICP company.
Step 2 — Enrich the engager
swan-enrich-contact with the LinkedIn URL. Returns: title, company, tenure, role family.
Cheap and necessary. The engager's title + company are the two things that determine the right reply.
Step 3 — ICP and CRM check in parallel
Two checks:
- ICP fit — does the engager's company match the org's ICP? Use
swan-search-companiesfor the domain; if not in Swan, briefly check firmographic match. - CRM relationship —
hubspot-search-objects(contacts, filter by email or LinkedIn URL). Is this person already in the system? Is there an active deal or owner?
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 First seen · 101 lines · 33 tokens per session scan A 09af7477c0a1
post-radar is a skill published in the GitHub repository swan-gtm/gtm-skills (153 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 1,306 once invoked, about $0.0002 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.