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 benyki/gtm-engine --skill engine-socialgit clone --depth 1 https://github.com/benyki/gtm-engineWrote 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/benyki/gtm-engine/engine-social)<a href="https://agentmods.dev/skills/benyki/gtm-engine/engine-social"><img src="https://agentmods.dev/badge/skills/benyki/gtm-engine/engine-social/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/benyki/gtm-engine/engine-social"><img src="https://agentmods.dev/badge/skills/benyki/gtm-engine/engine-social.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00116 | $0.05144 |
| Opus 5.5 | $0.00046 | $0.02058 |
| Sonnet 5.5 | $0.00023 | $0.01029 |
| Haiku 4.5 | $0.00012 | $0.00514 |
Grade A, and why
engine-social 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 1mo 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 — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
engine-social
Short-form written posts for LinkedIn, X, Bluesky, and other text social
channels. Much shorter feedback loop than engine-seo — you learn what works
in weeks rather than months.
This skill stands alone. It shares ideas with engine-seo and repeats some
of them in its own words, on purpose: the two engines are validated against
different evidence (a feed versus a search result), they'll drift apart as each
learns, and neither should be able to break the other. Everything this engine
needs is in its references/. Don't reach into another skill's folder.
This skill runs any engine folder of type social. The default folder
is social/; paths below (inputs/, templates/, runs/) are inside that
folder, while brand, accounts and keys are in shared/. Feel free to run
several social engines — social/ and social-founder-brand/ with
different goals and metrics are two independent folders — scaffold with
--merge --engine social-founder-brand:social, or copy one and empty its
runs/ and reports/ (history belongs to the original). Channels stay platform-named (linkedin, x,
bluesky, …).
How (not just what):
| Step | Reference |
|---|---|
| Find and validate subjects | references/subject-finding.md |
| Platforms / threads in the browser | references/browser-research.md |
| Cut AI slop / keep voice — every batch, every run | references/anti-slop-writing.md |
| Pre-built post parts with variations (optional) | templates/blocks/README.md (in the home) |
| Pick an image, or edit one via an image API (optional) | references/images.md |
| Write a thread + post on X / LinkedIn (browser) | references/threads-and-x.md |
| Post on Bluesky (API) | references/bluesky-post.md |
Paths in this file: shared/… means the gtm home (~/gtm by default, or
$GTM_HOME); templates/, inputs/, runs/ and reports/ mean the engine
folder you're running, wherever it lives. The scripts resolve both through
~/gtm/engines.json, so read them as names rather than literal paths.
What ships with it
7 files 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.
- 1mo ago Changed c870d63a1418
- 2mo ago First seen · 376 lines · 116 tokens per session scan A 058764178476
engine-social is a skill published in the GitHub repository benyki/gtm-engine (4 stars, last pushed 6d ago), licensed MIT. It adds 116 tokens to every session and 5,144 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-31.
engine-social compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| engine-socialbenyki/gtm-engine | Skill | 4 | 6d ago | MIT | A | 116 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |