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 tonydzi/second-brain-starter-kit --skill contrib-watchgit clone --depth 1 https://github.com/tonydzi/second-brain-starter-kitWrote 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/tonydzi/second-brain-starter-kit/contrib-watch)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/contrib-watch"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/contrib-watch/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/tonydzi/second-brain-starter-kit/contrib-watch"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/contrib-watch.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 | $0.00054 | $0.07382 |
| Opus 5.5 | $0.00022 | $0.02953 |
| Sonnet 5.5 | $0.00011 | $0.01476 |
| Haiku 4.5 | $0.00005 | $0.00738 |
Grade A, and why
contrib-watch scanned grade A with 2 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -H "Authorization: Bearer $GITHUB_FLEET_FULL_PAT" \ Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
r=subprocess.run(["gh","api","--paginate","--slurp",p],capture_output=True,text=True) How it starts
The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/contrib-watch — кто пришёл к нам сам, и почему мы обязаны ответить сегодня
Закон
Молчание в живом треде = провал, а не осторожность (CLAUDE.md §4.7). Ответ на GitHub я даю САМ, без «+» Антона и без гейта Наташи. Мерж кода — по [[github-publish-autonomous]] + leak-scan.
Порог: 24 часа. Дольше — красное. Обоснование не теоретическое: 05.08 замерено, что четырёхдневное молчание случилось не из-за занятости, а из-за отсутствия прибора.
Шаг 1 — снять картину (0 токенов)
⚠️ ПЕРЕД ЛЮБЫМ СКАНОМ СВЕРЬ АККАУНТ ВЫЗОВОМ, А НЕ ЯРЛЫКОМ (замер 02.10.2026): gh auth status
на этом узле печатает Logged in to github.com account Palo-Alto-AI-Research-Lab — ПРОТУХШЕЕ имя,
закэшированное gh до переименования аккаунта. Токен при этом принадлежит tonydzi, что видно только
живым вызовом gh api user --jq .login. Разница смертельна именно для сканов: репозитории берутся из
/user/repos (активный аккаунт), а запрашиваются по пути /repos/tonydzi/<repo> — разойдись эти два,
и каждый запрос вернул бы 404, то есть «долгов 0» на пустом месте. Ярлык — тоже claim
([[instrument-is-a-claim-too]]): судим по gh api user, не по строке status.
python ~/.claude/scripts/contrib_watch.py --html "$OBSIDIAN_VAULT/_Dashboards/Contrib-Inbox.html"
Обходит все наши non-fork репозитории — и публичные, И ПРИВАТНЫЕ, — находит треды, где ПОСЛЕДНИМ говорил внешний человек, считает часы ожидания, отмечает 🆕 тех, кого не видели ни разу. Exit 3 = есть просрочка.
⚠️ ПРИВАТНЫЕ СМОТРИМ ТОЖЕ (замер 24.09.2026, снят фильтр not r["private"]). Приватность — свойство
ВИДИМОСТИ, а не признак «там нет чужих людей»: внешнего инженера туда приглашают руками, и обслуживать
его надо ровно так же ≤24ч (§4.7). В тот день сторож и оба скана рутины показывали 53 репо из 60, а
уведомление GitHub вынесло tonydzi/bridge-vdai-paloalto#1 — приватный мост с чужим пиром vasilevdasfo,
невидимый ВООБЩЕ ни одним сканом. Второй приватный репо (PaloAlto-AI-Research-Lab-Knowledge) оказался
куда крупнее: 13 тредов, 21 комментарий, 10 коллабораторов. Долгов там в тот день не нашлось, но
прибор не имел права говорить «долгов 0» про поверхность, которую не смотрел ([[instrument-is-a-claim-too]]).
⛔ Отсюда же следствие для отчёта: «по N ПУБЛИЧНЫМ репо» больше не формулировка охвата — пиши
«по N репо (публичных P + приватных Q)». Тест охвата: _test_contrib_watch_private.py (красный доказан
на самом фильтре: охват был ['pub']).
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 Changed · +114 lines · -88 tokens per session 33014d7b8730
- 11d ago Changed · -1 lines bd5cbcfbfac4
- 16d ago Changed · +13 lines 3740a9c4c027
- 25d ago First seen · 189 lines · 142 tokens per session scan A fba8ad0a3488
contrib-watch is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (9 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 7,382 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-24.
Other skills, from other repositories
gh-issue-submit
A skill for submitting GitHub issues with the `gh` command-line tool. It guides issue-template discovery, duplicate checking, source investigation, submission, and verification.
ll-iteration-dev
A workflow for developing several tasks in parallel using separate Git worktrees, which are independent working directories for one repository.
canvas
Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.
obsidian-markdown
Explain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block references, math, and Mermaid. Use when the user explicitly requests Obsidian note formatting or syntax help, not for general Markdown or broad vault operations.
wiki-fold
Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit…
wiki
Initialize, adopt, and route work for a separate Obsidian knowledge vault through the portable claude-obsidian core. Use for vault setup, scaffolding, workspace selection, cross-project configuration, or choosing the correct wiki sub-skill. Triggers: /wiki, set up wiki, scaffold vault, create knowledge base, adopt…