post

post is a command for Claude Code from Vibiz-ai/vibiz-claude-plugin. It costs 16 tokens per session (889 once invoked), scanned A, original, MIT.

A command that turns a recent code commit into a draft social-media post and a matching image, with an option to schedule or publish it.

In plain words
What is it for?
Use it to create a social post from a meaningful commit, match it to the project’s brand, generate an image, and optionally schedule or publish the result.
Why use it?
It filters out small, routine, merged, or sensitive changes before preparing promotional content, reducing the chance of posting unsuitable work.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: positional $N argument.

Part of the vibiz plugin — 2 skills, 7 commands, 1 agent, 1 hook, 1 MCP server shipped together

Good fit Use it to create a social post from a meaningful commit, match it to the project’s brand, generate an image, and optionally schedule or publish the result.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/vibiz-ai/vibiz-claude-plugin/post
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Vibiz-ai/vibiz-claude-plugin

Made for: Claude Code.

Or install vibiz, the plugin that ships this one along with the rest of its 2 skills, 7 commands, 1 agent, 1 hook, 1 MCP server.

Wrote 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.

agentmods badge for post

README.md
[![agentmods](https://agentmods.dev/badge/commands/vibiz-ai/vibiz-claude-plugin/post/github.svg)](https://agentmods.dev/commands/vibiz-ai/vibiz-claude-plugin/post)
Your own site
<a href="https://agentmods.dev/commands/vibiz-ai/vibiz-claude-plugin/post"><img src="https://agentmods.dev/badge/commands/vibiz-ai/vibiz-claude-plugin/post/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.

agentmods 80×15 button for post

Your own site · 80×15
<a href="https://agentmods.dev/commands/vibiz-ai/vibiz-claude-plugin/post"><img src="https://agentmods.dev/badge/commands/vibiz-ai/vibiz-claude-plugin/post.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 889 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00016 $0.00889
Opus 5 $0.00008 $0.00445
Sonnet 5 $0.00003 $0.00178
Haiku 4.5 $0.00002 $0.00089

Measured 8d ago against content hash db1292df0341, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

post 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 8d 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.

plugins/vibiz/commands/post.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/vibiz:post

Turn a code change into a marketing-ready social post. Reads the latest commit (or a specific SHA passed as $1), writes draft post text in the brand voice, generates a matching image, and offers to schedule/publish it.

Steps

  1. Pick the commit.
    • If $1 is set, use it: git show --stat $1 and git log -1 --format='%H %s%n%b' $1.
    • Else: git log -1 --format='%H %s%n%b' and git diff HEAD~1 HEAD --stat.
  2. Filter out commits that are bad post material. Skip + tell the user, do NOT proceed silently:
    • Merge commits (git rev-list --merges -n 1 <sha> returns the sha)
    • Diff stat is fewer than 5 lines changed
    • Commit subject matches /^(chore|build|ci|style|docs)(\(|:)/i (boring infra)
    • Commit subject contains: password, secret, token, cve, vuln, xss, sqli, auth bypass (security/sensitive)
    • Commit body has [skip-vibiz] or [no-post]
  3. Pick the vibiz via the project-match skill:
    • Detect this project's brand URL (package.json homepage → pyproject → Cargo → README first link).
    • Call list_vibiz and match by websiteUrl. If exactly one match, use it silently. If multiple matches, ask the user which one. If zero matches, surface that and suggest /vibiz:onboard (do NOT silently fall back to "the only vibiz" or "the first vibiz").
  4. Draft the post. Compose 2-3 short copy variants (Twitter/X-friendly: under 280 chars each) that:
    • Lead with the user-visible benefit ("now you can …", "we just shipped …", "fixed the X annoyance"), NOT internal jargon
    • Avoid file paths, function names, library versions
    • Include a relevant emoji at the start (1 max)
    • End with a soft CTA ("try it →" or "ship it now →") only if the brand has a website to link to
  5. Generate a matching image. Call mcp__vibiz__vibiz_generate_image({ target: { vibiz: "<slug>" }, prompt: "<short visual prompt derived from the commit>", platform: "instagram_portrait", style: "branded-ad", useBrand: true }).
  6. Show the user. Output:
    • The draft variants (numbered)
    • The image viewUrl from step 5
    • Three options: 1) post it now, 2) schedule it, 3) just give me the draft
  7. If user picks 1 or 2:
    • Call mcp__vibiz__vibiz_social_list_accounts({ target: { vibiz: "<slug>" } }). If empty + connectUrl returned, surface the connect link and stop.
    • Otherwise ask which platform(s), pick the matching accountIds, and call mcp__vibiz__vibiz_social_publish with the chosen variant + image URL + (for option 2) a scheduledFor ISO datetime the user provides.

Read the full file on GitHub · 44 lines

Changes

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.

  1. 8d ago First seen · 44 lines · 16 tokens per session scan A db1292df0341

Subscribe to this mod's changes

post is a command published in the GitHub repository Vibiz-ai/vibiz-claude-plugin (7 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 889 once invoked, about $0.0001 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.