What is social-draft-and-approval?

A safety-focused method for monitoring authorized social accounts and preparing possible replies or posts for human review. It keeps proposed public actions in an approval queue rather than publishing them automatically.

Use it to summarize posts and engagement, identify unanswered questions, and prepare replies, posts, follows, likes, or messages for approval.

It separates drafting from publishing, reducing the risk of an unwanted public message or account action. It also organizes activity summaries and the reasons behind each draft.

social-draft-and-approval — Skill for Claude Code and Codex by Akakaui

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.

Any agent

npx skills add Akakaui/visual-browser-agent --skill social-draft-and-approval

Clone the repo

git clone --depth 1 https://github.com/Akakaui/visual-browser-agent

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/akakaui/visual-browser-agent/social-draft-and-approval/github.svg)](https://agentmods.dev/skills/akakaui/visual-browser-agent/social-draft-and-approval)

Your own site

<a href="https://agentmods.dev/skills/akakaui/visual-browser-agent/social-draft-and-approval"><img src="https://agentmods.dev/badge/skills/akakaui/visual-browser-agent/social-draft-and-approval/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/akakaui/visual-browser-agent/social-draft-and-approval"><img src="https://agentmods.dev/badge/skills/akakaui/visual-browser-agent/social-draft-and-approval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 829 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.

Model	Per session	Once invoked
Fable 5.1	$0.00034	$0.00829
Opus 5	$0.00017	$0.00415
Sonnet 5	$0.00007	$0.00166
Haiku 4.5	$0.00003	$0.00083

Measured 9d ago against content hash f6c156462bca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

social-draft-and-approval 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.

skills/social-draft-and-approval/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to Use

Use this skill for social platform work on authorized accounts:

Monitoring selected public pages/profiles
Summarizing recent posts and engagement
Drafting replies, comments, posts, and content ideas
Building an approval queue for potential public actions

Core Principle

The agent DRAFTS; humans DECIDE. By default EVERY public action - comment, message, follow, like, post - requires explicit approval. No exceptions.

Instructions

Monitoring (read-only)

navigate(url) to each selected public page
inspect_page() to read recent posts, timestamps, engagement counts
Summarize per page: themes, notable posts, unanswered questions
Never like, follow, comment, or message during monitoring passes

Drafting

Each draft must contain:

targetPost - URL, author, and snippet being responded to
account - the authorized account that would act
actionType - reply | post | follow | like | message
content - the full drafted text
rationale - why this adds value

Store drafts in the approval queue. Do NOT call submit_public_action.

Approval Queue Flow

Batch drafts with request_approval(drafts[], mode: "batch")
Present: account, action, target, full text, risk notes
Approved → schedule; Rejected → discard and log the reason
Only after explicit approval may submit_public_action fire
Audit-log every outcome: timestamp, approver, result

Rate Limits

Honor configured per-account daily caps per platform
Space approved actions apart - never burst-submit
On platform warnings/errors: back off immediately and pause the queue

Duplicate Content Detection

Before queuing, compare each draft against:

Content recently submitted on the same account
Other queued drafts targeting the same post Near-identical drafts are flagged duplicate for rework, never auto-sent.

Account Separation

Work one account context at a time; never mix drafts across accounts
Tag every draft and action with its owning account ID
Never cross-post identical content to multiple accounts

Read the full file on GitHub · 103 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.

9d ago First seen · 103 lines · 34 tokens per session scan A f6c156462bca

Subscribe to this mod's changes

social-draft-and-approval is a skill published in the GitHub repository Akakaui/visual-browser-agent (0 stars, last pushed 16d ago), licensed MIT. It adds 34 tokens to every session and 829 once invoked, about $0.0002 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.

Marketing and SEO

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens