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.
npx skills add aadarshvelu/syndicate --skill syndicate-ingest-twittergit clone --depth 1 https://github.com/aadarshvelu/syndicateWrote 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/skills/aadarshvelu/syndicate/syndicate-ingest-twitter)<a href="https://agentmods.dev/skills/aadarshvelu/syndicate/syndicate-ingest-twitter"><img src="https://agentmods.dev/badge/skills/aadarshvelu/syndicate/syndicate-ingest-twitter/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.
<a href="https://agentmods.dev/skills/aadarshvelu/syndicate/syndicate-ingest-twitter"><img src="https://agentmods.dev/badge/skills/aadarshvelu/syndicate/syndicate-ingest-twitter.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00026 | $0.00496 |
| Opus 5 | $0.00013 | $0.00248 |
| Sonnet 5 | $0.00005 | $0.00099 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
syndicate-ingest-twitter 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 12d 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.
What it actually says
/syndicate-ingest-twitter
You are running Twitter ingestion via a Playwright-controlled Chrome profile. This writes to the DB and launches Chrome — only run when the user explicitly asked.
Step 1 — preflight
Run status and check env_present.CHROME_EXECUTABLE and
env_present.CHROME_PROFILE_DIR. If either is false, tell the user how
to set them (see syndicate's README) and stop. The scraper will refuse to
authenticate without a valid persistent profile.
Step 2 — scrape
Default lookback is 2 days. Parse $ARGUMENTS for --days N (default 2)
and --headless true|false (default true — matches launchd):
cd "${SYNDICATE_REPO:-$(pwd)}" && uv run python -m pipeline.cli ingest-twitter --days ${days:-2} --headless ${headless:-true}
This can take 5–20 minutes depending on how many handles are configured and how active they've been. The skill runs in a forked subagent context so progress logs don't pollute the parent agent's history.
Step 3 — report
One line:
✓ twitter · fetched=X saved=Y skipped=Z failed=W
If failed > 0, surface error patterns: strict-mode locator violations,
captcha pages, X.com rate limits, or persistent-profile auth loss all show
up here. For auth loss specifically, the remediation is to re-run
scripts/setup_agent.sh and re-do the manual X login.
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.
- 12d ago First seen · 52 lines · 26 tokens per session scan A 014271e8cb25
syndicate-ingest-twitter is a skill published in the GitHub repository aadarshvelu/syndicate (2 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 496 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.
Other skills, from other repositories
blocked-page-recovery
Use when a fetch fails: 403/429, paywall, WAF, bot wall.
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.
broken-link-checker
Scans a website to find broken links (404s, 500s). Crawls internal pages, identifies broken outbound links, and reports source pages for easy fixing. Use this when the user asks to "check for broken links", "find 404s", "audit my links", or "is my site healthy".
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.
firecrawl-build-scrape
Integrate Firecrawl /scrape into product code for single-page extraction. Use when an app already has a URL and needs markdown, HTML, links, screenshots, metadata, or structured page output. Prefer this skill over broader crawl patterns when the feature is page-level.
browser
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.