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.
git clone --depth 1 https://github.com/KunanonJ/ai-skills-hubWrote 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/kunanonj/ai-skills-hub/instagram-reel-pipeline)<a href="https://agentmods.dev/commands/kunanonj/ai-skills-hub/instagram-reel-pipeline"><img src="https://agentmods.dev/badge/commands/kunanonj/ai-skills-hub/instagram-reel-pipeline/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/commands/kunanonj/ai-skills-hub/instagram-reel-pipeline"><img src="https://agentmods.dev/badge/commands/kunanonj/ai-skills-hub/instagram-reel-pipeline.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 | $0.00000 | $0.00440 |
| Opus 5 | $0.00000 | $0.00220 |
| Sonnet 5 | $0.00000 | $0.00088 |
| Haiku 4.5 | $0.00000 | $0.00044 |
Grade A, and why
instagram-reel-pipeline 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.
What it actually says
Instagram Reel Pipeline
Run Roman Knox's 4-stage Instagram Reels content pipeline interactively.
Source: https://www.threads.com/@roman.knox/post/DYRjSy8CF85
Steps
-
Ask for the niche (e.g.,
personal finance for Gen Z,luxury travel,productivity for ADHD). Wait for the user's answer. -
Ask which stage(s) to run:
all— full pipeline in order1— niche validation only (skill:instagram-reel-niche-validator)2— script architecture only (skill:instagram-reel-script-writer, needs a [topic])3— automation blueprint only (skill:instagram-reel-automation-blueprint)4— hook engineering only (skill:instagram-reel-hook-engineer)
-
For each requested stage, invoke the corresponding skill via the Skill tool with the user's niche substituted into the prompt.
-
For
allrun in this order: 1 → 2 → 4 → 3.- After Stage 1, pause and ask the user which of the 5 angles to pass into Stage 2 as
[topic]. - After Stage 4, summarise which hook variant to A/B test first.
- After Stage 1, pause and ask the user which of the 5 angles to pass into Stage 2 as
-
Surface caveats up front:
- If no web tool is attached (Exa, Tavily, Apify, Firecrawl,
browse, etc.), warn that Stages 1, 3, and 4 will produce inference-based output rather than real trend data. Offer to useexa-searchortavily-automationto ground the results. - Flag that the "1.5M views / $6,783 in 7 days" claim is the creator's marketing, not benchmark.
- If no web tool is attached (Exa, Tavily, Apify, Firecrawl,
-
Output format: render each stage's result as a clearly delimited markdown section, with the stage number, title, and the input parameters used. End with a "next action" line.
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 · 29 lines · 0 tokens per session scan A 70ce30987120
instagram-reel-pipeline is a command published in the GitHub repository KunanonJ/ai-skills-hub (5 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 440 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 2026-09-03.
Other commands, from other repositories
sdd-continue
Continue the next SDD phase in the dependency chain.
sdd-apply
Implement SDD tasks — writes code following specs and design.
sdd-explore
Explore and investigate an idea or feature — reads codebase and compares approaches.
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
gentle-sdd-ff
Fast-forward all SDD planning phases — proposal through tasks.
constitution
A command for creating or updating a project's constitution, a document that records its governing principles and working rules, in Simplified Chinese.