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 agentmods add skills/internet-development/ts-general-agent/github-announcementnpx skills add internet-development/ts-general-agent --skill github-announcementgit clone --depth 1 https://github.com/internet-development/ts-general-agentWhat 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 | $0.00018 | $0.00310 |
| Opus 5 | $0.00009 | $0.00155 |
| Sonnet 5 | $0.00004 | $0.00062 |
| Haiku 4.5 | $0.00002 | $0.00031 |
Grade A, and why
GitHub Announcement 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 2d 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
Announcement Decision
You just completed something on GitHub. Decide if it's worth announcing on Bluesky.
Context: {{context}}
Announcement type: {{announcementType}}
Decision criteria for PRs:
- Are you genuinely proud of this work? Not every PR deserves a post.
- Did you solve an interesting technical problem worth sharing?
- Would the community find this useful, educational, or interesting?
- Is this a meaningful contribution, not just a minor fix?
Decision criteria for Issues:
- Does this issue raise a question worth community discussion?
- Is this something others might have opinions on or want to contribute to?
- Would sharing this invite valuable perspectives?
Respond with ONLY "yes" or "no" — nothing else. Be selective. Most work doesn't need announcing.
Bluesky Post
Compose a short Bluesky post about this GitHub activity. Be authentic — write in your own voice from SELF.md.
Context: {{context}}
Guidelines:
- Keep it under 300 graphemes — that's the Bluesky platform limit. Be concise and punchy
- Share what you learned or what's interesting about this, not just "I made a PR"
- Include the URL so people can check it out
- Don't be self-congratulatory — be genuinely helpful or thought-provoking
- Write like you're telling a friend about something cool you worked on
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.
- 2d ago First seen · 41 lines · 18 tokens per session scan A 09603d664be0
GitHub Announcement is a skill published in the GitHub repository internet-development/ts-general-agent (11 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 310 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 2026-08-30.
Other skills, from other repositories
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
content-planner
WeChat Official Account topic planning and content calendar management. Based on WeChat article search and trending analysis, generates differentiated topic recommendations and outputs structured content calendars. Activated when users mention "topic", "planning", "content calendar", "trending", or "what to write next…
launch-graphics
Generate agentOS marketing/launch graphics (launch & social heroes, code-snippet cards) from the committed generators in docs-internal/graphics. Use when asked to make, update, or render an agentOS launch image, social image, "agentOS Apps" graphic, or technical code-snippet image.
competitive-analysis
Competitive landscape analysis: positioning, scorecards, moat assessment, market share trends.
competitor-product-monitor
Monitor competitor product releases and new feature announcements. Use this skill when the user wants to track what competitors are shipping, find the latest product launches in their industry, or generate a competitor release report. Triggers include phrases like "track competitor releases", "what are my competitors…
find-selling-points
Mine the codebase for capabilities worth telling people about — the surprising, user-facing ones — and prove each against source before it may be published. Use when writing or auditing marketing copy, a landing page, a README, a launch post, or when asked "what is actually good about this" / "找卖点" / "提炼宣传点".