Borrowing it
Nothing to install: this file belongs to cybertronai/SutroYaro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cybertronai/SutroYaro/main/.claude/skills/sutro-sync/SKILL.mdgit clone --depth 1 https://github.com/cybertronai/SutroYaroWrote 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/cybertronai/sutroyaro/sutro-sync)<a href="https://agentmods.dev/skills/cybertronai/sutroyaro/sutro-sync"><img src="https://agentmods.dev/badge/skills/cybertronai/sutroyaro/sutro-sync.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 | $0.00034 | $0.01035 |
| Opus 5 | $0.00017 | $0.00517 |
| Sonnet 5 | $0.00007 | $0.00207 |
| Haiku 4.5 | $0.00003 | $0.00103 |
Grade A, and why
sutro-sync 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sutro Sync Routine
Run this at session start and before any push. Covers three sources: Telegram, Google Docs, GitHub.
1. Telegram (daily)
bin/tg-sync
Syncs 6 forum topics to a local SQLite database (telegram.db). First run does a full backfill; subsequent runs are incremental (only new messages).
Query recent messages from priority topics to check for new questions, directions, or results:
sqlite3 telegram.db "SELECT date, sender, substr(text, 1, 150) FROM messages
WHERE topic_id IN (SELECT id FROM topics WHERE slug IN ('chat-yad', 'chat-yaroslav', 'challenge-1-sparse-parity'))
AND date > datetime('now', '-3 days')
ORDER BY date DESC LIMIT 15"
Report anything relevant to the user.
Fallback: If telegram.db doesn't exist and credentials aren't configured, read the committed JSON files in src/sparse_parity/telegram_sync/ instead (may be stale).
Prerequisites: bun install, .env with TELEGRAM_API_ID and TELEGRAM_API_HASH, tg auth login (one-time). Full setup: docs/tooling/telegram-setup.md.
2. Google Docs (weekly, after Monday meetings)
python3 src/sync_google_docs.py
Pulls 15+ Google Docs to docs/google-docs/. After syncing:
- Check
docs/google-docs/sutro-group-main.mdfor new meeting doc links - If new docs found, add them:
python3 src/sync_google_docs.py --add "URL" "name" "Description" python3 src/sync_google_docs.py # re-run - Add cross-reference headers (
!!! infoadmonition) to new docs - Add new pages to
mkdocs.ymlnav under Meetings > Google Docs - Update
docs/meetings/index.mdanddocs/meetings/notes.md
Prerequisites: pandoc (brew install pandoc). Docs must be "Anyone with the link" sharing.
3. GitHub (daily)
gh pr list --repo cybertronai/SutroYaro --state open
gh issue list --repo cybertronai/SutroYaro --state open
Check for new PRs from contributors (Andy/zh4ngx, Michael, others). Review code, verify results are reproducible, check that DISCOVERIES.md is updated.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 113 lines · 34 tokens per session scan A ac4a38c2e489
sutro-sync is a skill published in the GitHub repository cybertronai/SutroYaro (16 stars, last pushed 3mo ago), licensed Unlicense. It adds 34 tokens to every session and 1,035 once invoked, about $0.0002 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
proof-orchestrator
Manage a stateful, run-directory-based proof project: continuation across runs, run-local source bookkeeping, manual GPT Pro handoff packages when a local attempt stalls, and an optional DeepSeek second opinion as additional evidence only. Use when the user asks for proof-run orchestration, a GPT Pro handoff, or…
feishu-notify
A utility for sending status notifications to Feishu, also known as Lark, a workplace messaging and collaboration app. It can work through a bot webhook and may support interactive approval or reply messages when configured.
caveman
Ultra-compressed reply mode. Cuts output tokens 65-75% by answering in terse "caveman" style while keeping full technical accuracy, and shapes what survives: action first, state restated every turn, concrete time estimates, visible wins. Intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full…
desktop-sessions-discovery
Discover, search, and selectively restore Claude desktop app sessions hidden across multiple accountIds. Use when user mentions "missing sessions after account switch", "lost desktop sessions", "where do my old sessions live", or runs multiple Claude accounts on the same machine. Do NOT use for Claude Code CLI session…
rigorous-research
Conduct AI/ML research as a science - first-principles reasoning, mechanism-level hypotheses, falsifiable predictions, discriminative experiments, honest evaluation, and claims that survive hostile review. Use when starting or steering an AI/ML research project, deciding what to investigate next, choosing datasets…
hello_workflow
You are an AI assistant helping users understand and create Pipulate workflows. When users interact with the Hello World workflow, your job is to.