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 tang-vu/social-posting-skills --skill post-xgit clone --depth 1 https://github.com/tang-vu/social-posting-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/tang-vu/social-posting-skills/post-x)<a href="https://agentmods.dev/skills/tang-vu/social-posting-skills/post-x"><img src="https://agentmods.dev/badge/skills/tang-vu/social-posting-skills/post-x/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/tang-vu/social-posting-skills/post-x"><img src="https://agentmods.dev/badge/skills/tang-vu/social-posting-skills/post-x.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 | $0.00018 | $0.00518 |
| Opus 5.5 | $0.00007 | $0.00207 |
| Sonnet 5.5 | $0.00004 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
post-x 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
X (Twitter) Adapter
Machine-checkable facts (char limits, media bounds, publish modes) live in
platforms/x.json — the CLI validates against them. Do not hardcode numbers
here; they go stale.
What X rewards (culture, not algorithm folklore)
- One sharp claim per post. The hook decides whether a thread gets read.
- Threads that teach: numbered steps, one idea per post, 5–10 posts.
- Build-in-public: real numbers, real decisions, real failures.
- Conversation over broadcasting — replies are where accounts grow.
Drafting from the content graph
core-claim→ post 1 (hook). Cut adjectives; keep the strongest noun/verb.proof/technicalnodes → thread posts 2..n, one per post.cta+link→ last post, or a self-reply (see link note).- Disclosures belong IN the content: "I built this" reads natively on X.
Link note (heuristic, labeled)
Widely held community practice: put the external link in a self-reply rather
than the main post, to keep the post clean. The reach impact is a heuristic —
the platform data marks it community-heuristic, not a documented rule.
Publishing
agent-browser→ executeplaybook.jsonliterally: composer selectors, "add to thread" for chains, bounded waits, verify once after Post.api→ official X API exists but is paid-tier; adapter not implemented.manual→ draft package with the full thread laid out.
On any challenge, ambiguous composer state, or uncertain post state: STOP and
report unknown — never re-submit.
Genuine engagement (human participation)
- Reply substantively to comments on your post — add information, not "thanks!".
- Participate in your niche between posts because you have something to say, not as a distribution ritual.
- Do NOT mass-like, mass-follow, or recycle identical replies. These are the behaviors platforms penalize and this project prohibits.
Pitfalls
- Typing via automation: chunk long text; emoji/unicode may not type.
- Rate limits are real — campaign volume should stay far below caps.
- Identical text cross-posted verbatim reads as spam; adapt per platform.
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.
- 1mo ago Changed · -174 lines · +5 tokens per session 141a41a641eb
- 1mo ago First seen · 229 lines · 13 tokens per session scan A 2232c260833c
post-x is a skill published in the GitHub repository tang-vu/social-posting-skills (12 stars, last pushed 22d ago), licensed MIT. It adds 18 tokens to every session and 518 once invoked, about $0.0001 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.
Other skills, from other repositories
auto-research
Research uncertain questions with an explicit, user-approved web search or ChatGPT consultation, then present options and wait for implementation approval.
e2e-automator
Build robust end-to-end test suites with Playwright or Cypress. Covers page objects, fixtures, visual testing, and CI integration.
agentic-actions-auditor
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines.
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.
ad-campaign-analyzer
Analyze cross-channel campaign data, quantify uncertainty, and propose evidence-labeled budget tests without overstating causality.
apk-redteam-pipeline
End-to-end Android APK red-team pipeline.