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.
git clone --depth 1 https://github.com/iker-gonzalez/antwork-skillsWrote 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/agents/iker-gonzalez/antwork-skills/antwork-content)<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>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 | $0.00058 | $0.00624 |
| Opus 5 | $0.00029 | $0.00312 |
| Sonnet 5 | $0.00012 | $0.00125 |
| Haiku 4.5 | $0.00006 | $0.00062 |
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.
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)
list_posts(status published) — recent published copy across accounts.get_post(post_id) — pull the full text + metrics for the standout and the weakest few, to read the actual words.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>
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.
- 7d ago First seen · 40 lines · 58 tokens per session scan A a6287ac619f8
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.