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 content-writinggit 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/content-writing)<a href="https://agentmods.dev/skills/tang-vu/social-posting-skills/content-writing"><img src="https://agentmods.dev/badge/skills/tang-vu/social-posting-skills/content-writing/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/content-writing"><img src="https://agentmods.dev/badge/skills/tang-vu/social-posting-skills/content-writing.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 | $0.00022 | $0.00622 |
| Opus 5.5 | $0.00009 | $0.00249 |
| Sonnet 5.5 | $0.00004 | $0.00124 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
content-writing 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Writing (Campaign Layer)
You adapt the canonical content graph into platform-native drafts. The CLI
gives you structural scaffolds (campaign adapt); your job is the creative
pass that makes each worth reading — while keeping ONE fact layer.
Non-negotiables
- Facts come only from the graph/source/factBase. If a number isn't there, it doesn't exist. No invented metrics, no superlatives without evidence.
- Different tone per platform: YES. Different facts: NEVER.
- No engagement bait, no "link in bio" games, no algorithm superstition stated as fact. Label strategy advice as heuristic when it is one.
- Disclosures stay honest: "I built this", "Open source", "Sponsored".
Platform-native ≠ shorter
| Platform | Shape | Voice |
|---|---|---|
| X | hook → thread (1 idea/post) → CTA | punchy, direct |
| Threads | conversational chain | warm, casual |
| Bluesky | sincere short posts | early-adopter, human |
| outcome-led narrative, bullets | professional, first-person | |
| story + substance + feedback ask | transparent, humble | |
| Hacker News | plain factual title + tryable link | technical, zero marketing |
| Dev.to | tutorial/case study with code | helpful teacher |
| Product Hunt | tagline + features + maker story | confident, personal |
| community question + short body | friendly, plain | |
| IndieHackers | milestone + real numbers | transparent, tactical |
| Substack | issue with a point | personal essay |
| Medium | polished longform | essayistic |
Hook formulas (use honestly)
- Specific outcome: "Verify any AI model's reasoning — v1.0 is out."
- Story: "I spent 3 months on proof chains. Here's what I learned."
- Useful: "How to verify model outputs with Merkle proofs (OSS)."
- Contrarian-lite: "Most AI evals are vibes. Receipts are better." — only if you can back it.
- Never: fake urgency, "you're doing X wrong" clickbait, bait questions.
Structure patterns
Thread (X/Threads/Bluesky): hook → one node per post → CTA last. Article (Dev.to/Medium/Substack): lede → what/how → try it → next. Milestone (IH/LinkedIn): claim → context → numbers → lessons → ask. Show HN: "Show HN: Name — what it does" + usable link + honest text.
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 · -145 lines · +8 tokens per session dcacc3a137d9
- 1mo ago First seen · 205 lines · 14 tokens per session scan A c28b242d0a9e
content-writing is a skill published in the GitHub repository tang-vu/social-posting-skills (12 stars, last pushed 22d ago), licensed MIT. It adds 22 tokens to every session and 622 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.
apk-redteam-pipeline
End-to-end Android APK red-team pipeline.
ad-campaign-analyzer
Analyze cross-channel campaign data, quantify uncertainty, and propose evidence-labeled budget tests without overstating causality.