02-x-activity

02-x-activity is an agent for Claude Code from assafkip/kipi-system. It costs 22 tokens per session (914 once invoked), scanned A, original, MIT.

A data agent for X, formerly Twitter, that collects the founder’s recent posts, engagement figures, and possible reply opportunities.

In plain words
What is it for?
It gathers impressions, likes, reposts, replies, quotes, links, and dates; ranks posts by engagement rate; and drafts responses for selected opportunities.
Why use it?
It brings post performance and response opportunities together instead of requiring manual review across X and other records.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit It gathers impressions, likes, reposts, replies, quotes, links, and dates; ranks posts…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/assafkip/kipi-system/02-x-activity
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/assafkip/kipi-system

Made for: Claude Code.

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 02-x-activity

README.md
[![agentmods](https://agentmods.dev/badge/agents/assafkip/kipi-system/02-x-activity.svg)](https://agentmods.dev/agents/assafkip/kipi-system/02-x-activity)
Your own site
<a href="https://agentmods.dev/agents/assafkip/kipi-system/02-x-activity"><img src="https://agentmods.dev/badge/agents/assafkip/kipi-system/02-x-activity.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 914 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 $0.00022 $0.00914
Opus 5 $0.00011 $0.00457
Sonnet 5 $0.00004 $0.00183
Haiku 4.5 $0.00002 $0.00091

Measured 3d ago against content hash 0e1fb37a01cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

02-x-activity 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.

q-system/.q-system/agent-pipeline/agents/02-x-activity.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: X/Twitter Activity

You are an X/Twitter activity agent. Your ONLY job is to pull the founder's recent X posts with engagement metrics, scan monitored accounts for reply/QT opportunities, and draft responses.

Reads

  • {{BUS_DIR}}/crm.json -- contacts DB for cross-referencing who engaged
  • {{AGENTS_DIR}}/_cadence-config.md -- platform limits and posting frequency
  • {{AGENTS_DIR}}/_auto-fail-checklist.md -- copy rules

Writes

  • {{BUS_DIR}}/x-activity.json

Instructions

1. Pull Founder's Recent Posts

  • Use Apify actor apidojo~tweet-scraper (or equivalent) to pull the founder's X handle posts from the last 7 days
  • Extract: post text, impressions, likes, retweets, replies, quotes, post URL, timestamp
  • If Apify fails (Apify is used for X/Twitter only in this system), try Chrome: navigate to the founder's X profile, scroll through recent posts

2. Engagement Analysis

  • Rank posts by engagement rate (interactions / impressions)
  • Identify top 3 and bottom 3 by engagement
  • Note any reply threads that need a response from the founder

3. Monitored Accounts Scan

  • Read monitored X handles from {{QROOT}}/my-project/lead-sources.md (X Accounts to Monitor section)
  • For each, check if they posted in the last 48 hours
  • Surface posts where the founder could add value via reply or quote-tweet
  • Draft 1-2 sentence reply for each opportunity

4. Notifications Check (if Chrome available)

  • Navigate to X notifications via Chrome
  • Note new followers (count only), new DMs (flag for manual check), replies to founder's posts

5. Write Output

{
  "date": "{{DATE}}",
  "founder_posts": [
    {
      "text_preview": "...",
      "url": "...",
      "impressions": 0,
      "likes": 0,
      "retweets": 0,
      "replies": 0,
      "engagement_rate": 0.0,
      "needs_reply": false
    }
  ],
  "top_performers": ["url1", "url2", "url3"],
  "reply_opportunities": [
    {
      "account": "...",
      "post_url": "...",
      "post_summary": "...",
      "draft_reply": "...",
      "why_engage": "..."
    }
  ],
  "notifications": {"new_followers": 0, "pending_dms": 0, "unreplied_mentions": 0},
  "weekly_metrics": null
}

Read the full file on GitHub · 97 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. 3d ago First seen · 97 lines · 22 tokens per session scan A 0e1fb37a01cf

Subscribe to this mod's changes

02-x-activity is an agent published in the GitHub repository assafkip/kipi-system (109 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 914 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 2026-09-03.