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 instructions/huzaifa-ali/post-kit/agents-mdgit clone --depth 1 https://github.com/Huzaifa-ali/post-kitWrote 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/instructions/huzaifa-ali/post-kit/agents-md)<a href="https://agentmods.dev/instructions/huzaifa-ali/post-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/huzaifa-ali/post-kit/agents-md.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 | $0.00908 | $0.00908 |
| Opus 5 | $0.00454 | $0.00454 |
| Sonnet 5 | $0.00182 | $0.00182 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
post-kit AGENTS.md 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 3d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
post-kit
A zero-code content creation pipeline for any niche. Research, write, and polish posts that sound like you — for any platform.
How This Works
This project is a set of markdown instruction files that you (the AI agent) read and follow to help users create content.
First Run
Check if my-niche/niche.yaml exists.
- If it doesn't exist: Read and follow
engine/core/onboarding.mdto set up the user's pipeline. - If it exists: The user is set up. Follow the pipeline for any content request.
Pipeline
For every content request, follow engine/core/pipeline.md:
Dedup Check (FIRST — before anything else) → Research → Write → Voice Pass → Anti-AI Pass → Quality Gate → Output
⛔ CRITICAL: Dedup runs BEFORE research
The very first action for ANY content request (including "what's trending") is:
- Read
my-niche/niche.yaml→ resolve output path (output.path, defaults to../posts) - LIST the current month's posts folder (e.g.,
posts/2026-july/) — actually list it, get all folder names - Load that list into context
Do NOT run any web search or fetch any URL until you have completed step 2 above. This is a hard gate.
Files to read before writing any content:
my-niche/niche.yaml— user's identity and pillarsmy-niche/voice.md— how they soundmy-niche/content-rules.md— structure, length, hooks- Active platform file from
engine/platforms/(linkedin.md is default) engine/core/anti-ai-writing.md— mandatory pass (never skip)engine/core/quality-gates.md— every post must pass
Optional modules (only active if the file exists in my-niche/):
visual-system.md— image approachmemes.md— humor pipelinenews-scout.md— trending topic discoveryvideo-content.md— video creationimage-prompts.md— AI image promptsanalytics.md— performance trackingrepurpose.md— multi-platform adaptationcarousel.md— slide content
Commands the User Might Say
| User says | What to do |
|---|---|
| "write a post about [topic]" | Run the full pipeline |
| "what's trending" / "find me topics" / "what should I post about" | Use news-scout module → run "The Daily Scout Command" from my-niche/news-scout.md |
| "roast [topic]" / "meme about [x]" | Use memes module (if active) |
| "help me improve my [voice/hooks/etc]" | Follow engine/core/brainstorm.md |
| "humanize this" | Run anti-AI pass from engine/core/anti-ai-writing.md |
| "repurpose this for X" | Use repurpose module (if active) |
| "make a video" / "video about [x]" | Use video-content module (if active) |
| "update my niche" / "check for updates" / "what changed in post-kit" | Follow engine/core/update.md — reconcile niche with latest post-kit improvements |
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.
- 3d ago First seen · 78 lines · 908 tokens per session scan A d5c8ab78e850
post-kit AGENTS.md is an instructions file published in the GitHub repository Huzaifa-ali/post-kit (4 stars, last pushed 1mo ago), licensed MIT. It adds 908 tokens to every session, about $0.0045 per session on Opus 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 instructions, from other repositories
cc-sdd AGENTS.md
Instructions for gotalab/cc-sdd, covering agentic sdlc and spec-driven development, project context, paths, steering vs specification and active specifications.
marketing-machine CLAUDE.md
Instructions for cagatayuncu/marketing-machine, covering marketing-machine — contributor notes, commands, architecture in ten lines and invariants (violating these is a bug, not a style choice).
template GEMINI.md
Instructions for ai-plugin-marketplace/template, covering skill evaluator, usage and how it works.
cc-sdd CLAUDE.md
Instructions for gotalab/cc-sdd, covering agentic sdlc and spec-driven development, project context, paths, steering vs specification and active specifications.
wassden-mcp CLAUDE.md
Claude Code instructions for tokusumi/wassden-mcp, covering claude code instructions, linter and test policy, commands, development commands and cli testing commands.
todo-for-ai AGENTS.md
AGENTS.md instructions for todo-for-ai/todo-for-ai: These constraints are mandatory for all pages and components in this repository.