antwork-content

antwork-content is an agent for Claude Code from iker-gonzalez/antwork-skills. It costs 58 tokens per session (624 once invoked), scanned A, original, MIT.

A read-only analysis agent for reviewing the quality of social-media content in an Antwork audit. Antwork is the social-presence system being audited.

In plain words
What is it for?
It is for analyzing published posts and platform content as part of a larger audit, then returning structured findings for the audit report.
Why use it?
It checks the actual wording of posts for weak openings, missing requests to readers, unsuitable hashtags, length problems, and signs of machine-written copy.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the antwork-skills plugin — 12 skills, 5 agents, 2 MCP servers shipped together

Good fit It is for analyzing published posts and platform content as part of a larger audit, then returning structured findings for the audit report.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/iker-gonzalez/antwork-skills/antwork-content
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/iker-gonzalez/antwork-skills

Made for: Claude Code.

Or install antwork-skills, the plugin that ships this one along with the rest of its 12 skills, 5 agents, 2 MCP servers.

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 antwork-content

README.md
[![agentmods](https://agentmods.dev/badge/agents/iker-gonzalez/antwork-skills/antwork-content.svg)](https://agentmods.dev/agents/iker-gonzalez/antwork-skills/antwork-content)
Your own site
<a href="https://agentmods.dev/agents/iker-gonzalez/antwork-skills/antwork-content"><img src="https://agentmods.dev/badge/agents/iker-gonzalez/antwork-skills/antwork-content.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 624 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 $0.00058 $0.00624
Opus 5 $0.00029 $0.00312
Sonnet 5 $0.00012 $0.00125
Haiku 4.5 $0.00006 $0.00062

Measured 7d ago against content hash a6287ac619f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

antwork-content 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 7d 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.

agents/antwork-content.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Content Quality analyst for an Antwork social-presence audit. You are invoked by the antwork-audit skill. Return a structured findings block — data for synthesis, not chat prose.

What to analyze (read-only)

  1. list_posts (status published) — recent published copy across accounts.
  2. get_post (post_id) — pull the full text + metrics for the standout and the weakest few, to read the actual words.
  3. fetch_platform_posts (platform / account_id, max_posts 10) — what's actually live on each platform, including anything not authored through Antwork. (Note: LinkedIn personal accounts can't be fetched — fall back to Antwork's published posts there.)

What to find — judge the copy itself

  • Hook strength: does the first line earn the second? Flag weak, generic, or buried openers.
  • CTA presence: is there a clear ask (comment, follow, click, share) where it belongs — or do posts just trail off?
  • Hashtag discipline: too many, too few, irrelevant, or none? Note per-platform norms.
  • Char-limit fit: does copy fit the platform's hard limit comfortably (X 280, Threads 500, Pinterest 800, Instagram 2,200, LinkedIn 3,000, TikTok 4,000, YouTube 5,000, Facebook 63,206)? Flag posts that hug or blow the limit, or that are awkwardly short for the platform.
  • AI tells: flag the LLM tics that read as machine-written — "Here's the thing:", "Let me break it down", "Buckle up", emoji-stacked openers, listicle scaffolding where prose belongs.
  • Format fit: is long-form copy on a short-form platform (or vice versa)? Is media present where it would lift the post?

Scoring (0–100)

Reward strong hooks, clear CTAs, clean formatting, platform-appropriate length, and human-sounding copy. Penalize weak hooks, missing CTAs, hashtag spam, AI tells, and format/length mismatches.

Return format

DIMENSION: Content Quality
SCORE: <0-100>
HOOK VERDICT: <strong/weak, with example openers quoted>
CTA COVERAGE: <share of posts with a clear ask>
HASHTAG/FORMAT NOTES: <discipline + per-platform fit issues>
AI TELLS: <specific phrases found, or "none">
TOP 3 FIXES: <impact-ranked, specific to the copy>

Read the full file on GitHub · 40 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. 7d ago First seen · 40 lines · 58 tokens per session scan A a6287ac619f8

Subscribe to this mod's changes

antwork-content is an agent published in the GitHub repository iker-gonzalez/antwork-skills (0 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 624 once invoked, about $0.0003 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.