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 agentmods add commands/fatihkan/badi/content-generategit clone --depth 1 https://github.com/fatihkan/badiWrote 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/commands/fatihkan/badi/content-generate)<a href="https://agentmods.dev/commands/fatihkan/badi/content-generate"><img src="https://agentmods.dev/badge/commands/fatihkan/badi/content-generate.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01282 |
| Opus 5 | $0.00000 | $0.00641 |
| Sonnet 5 | $0.00000 | $0.00256 |
| Haiku 4.5 | $0.00000 | $0.00128 |
Grade A, and why
content-generate 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 4d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social media content generation command. Produces ready-to-use posts, captions, visual briefs, and hashtags for the given platform and type.
Required Tools
- Read (brand voice, previous content, project context) -- Write (content file) -- Grep (previous content scan) -- ...
Procedure (6 Steps)
1. Gather Input
- Platform: Instagram / Twitter-X / LinkedIn / TikTok / YouTube / Facebook / All
- Type: Informative (tips, lists, how-tos) / Inspirational (motivation, success) / Entertainment (memes, trends) / Sales (product, discount, launch) / ...
- Topic/Message: detail
- Tone: Friendly / Professional / Fun / Inspirational / Provocative / Minimal
- Visual brief wanted? (yes/no) -- ...
2. Brand Context
Mandatory: .claude/workspace/marka-sesi.md (tone, address style, emoji policy) -- memory.md (campaign/launch/project)
Optional: .claude/workspace/icerikler/ (last 5, repeat prevention) -- .claude/workspace/takvim/ (timing fit) -- knowledge-base.md (phrases to avoid, rules)
If no brand voice exists, suggest /content-brand-voice without making it mandatory.
3. Platform Rules
Instagram: post max 2200 chars (first 125 critical, cut-off point) -- hashtags 20-30 (niche+general, first comment also OK) -- visuals 1080x1080 or 1080x1350 -- ...
Twitter/X: max 280 chars (each tweet in a thread separate) -- thread: 1/ main message, 2-N/ support, last/ CTA -- hashtags 1-3 (more reads as spam) -- ...
LinkedIn: max 3000 chars (first 210 before "see more") -- tone professional + human, personal experience -- hashtags 3-5 (sector) -- ...
TikTok: caption max 2200 (keep it short) -- video first, text supporting -- hashtags 3-5 (trend + niche) -- ...
YouTube: title max 100 chars (keyword) -- description 5000 chars (first 2-3 lines SEO-critical) -- tags 10-15 -- ...
Facebook: post limit 63,206 but optimal 40-80 words -- asking a question lifts engagement -- link description short and clear
3.5 2026 Algorithm Reality (verify live)
Apply these so the output actually reaches — they trump the static limits above (delegate to the content-creator agent for the full playbook):
- Original or materially transformed only — Instagram de-recommends reposted/aggregated/watermarked content across Reels, photos AND carousels; strip foreign watermarks.
- AI assist OK, AI slop penalized — vary every asset and add genuine value; disclose realistic AI media (auto-detected via C2PA/SynthID, mandatory on major platforms; EU AI Act transparency lands 2026).
- Build for sends + watch-through — engineer DM-able, save-worthy content (sends-per-reach is the strongest IG signal); favor watch-time over sub-15s clips with mid-video hooks; lead with a fast payoff hook in the opening seconds, captions burned in (sound-off).
- Search-on-social — put the exact phrase people would search in the first caption line + on-screen text.
- Human over polish — visibly human, lo-fi, founder-led beats AI-perfect sameness in 2026.
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.
- 4d ago First seen · 82 lines · 0 tokens per session scan A ab072269885a
content-generate is a command published in the GitHub repository fatihkan/badi (7 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,282 tokens. 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 commands, from other repositories
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
sonarqube
Analyze SonarCloud quality issues for a specific PR.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary — the complete landing pipeline.
methodology-advisor
Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack.
scaffold
Interactive coach that asks 4-5 questions to determine whether you need an agent, command, skill, hook, or rule — then generates a ready-to-use template. Usage: /scaffold (no arguments — starts the coaching session).
investigate
Systematic root-cause debugging — find the cause before writing any fix.