Borrowing it
Nothing to install: this file belongs to haoxiang-xu/PuPu. 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/haoxiang-xu/PuPu/main/.claude/archive/retired/skills/org-sync/SKILL.mdgit clone --depth 1 https://github.com/haoxiang-xu/PuPuWrote 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/haoxiang-xu/pupu/org-sync)<a href="https://agentmods.dev/skills/haoxiang-xu/pupu/org-sync"><img src="https://agentmods.dev/badge/skills/haoxiang-xu/pupu/org-sync/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/haoxiang-xu/pupu/org-sync"><img src="https://agentmods.dev/badge/skills/haoxiang-xu/pupu/org-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 35 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
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 | $0.00082 | $0.03316 |
| Opus 5 | $0.00041 | $0.01658 |
| Sonnet 5 | $0.00016 | $0.00663 |
| Haiku 4.5 | $0.00008 | $0.00332 |
Grade A, and why
org-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 10d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PuPu Org Sync
You are running PuPu's periodic organization sync for the CEO (a solo founder). The org is 23 agents across 4 lines.
The deliverable is a decision list, not a report. The CEO's attention is the scarcest resource in this organization — it is the single bottleneck every org decision competes for. Every line you write costs some of it. A sync that produces a beautiful 3000-word health report and no decisions has failed.
The two phases
Phase 1 in-org sync — each line syncs internally, in parallel
Phase 2 cross-org sync — lines challenge each other's claims, then converge
Phase 3 decision list — what needs the CEO, what was already self-decided
Never skip Phase 2. In the 2026-07-28 unchain review, letting CTO and HR challenge each other directly caught a fatal evidence error (git authorship used to prove an agent had zero throughput) that no single department had caught alone. Cross-examination is where the value is. Do not replace it with a summary you write yourself — relaying through a middleman degrades the argument.
Scope
| Arg | Behavior |
|---|---|
| (none) | Full sync: all 4 lines + cross-org |
cto / coo / ai / hr |
In-org sync for that line only; skip Phase 2 |
--brief |
Full sync, but report only anomalies (see Output) |
The org (verify before dispatching — the chart goes stale)
find .claude/agents -name "*.md" ! -name "HYBRID_CODEX_POLICY.md" | sed 's|.*/agents/||' | sort
| Line | Head | Members |
|---|---|---|
| CTO | pupu-cto |
pupu-architect, chat-experience (chat-core, chat-bubble), config-extension (settings, agents, toolkit), platform-security (electron, security-expert), direct (backend, qa-tester, ux-designer, mcp-store-curator) |
| COO | pupu-coo |
pupu-growth-ops, pupu-market-analyst, pupu-release-full-test |
| AI | pupu-llm-expert |
pupu-ai-researcher |
| HR | pupu-hr-judge |
pupu-hr-comm-assessor, pupu-hr-context-assessor, pupu-hr-signal-assessor, pupu-hr-route-assessor (court model, 2026-08-04 reorg; summoned via org-court, contribution is not an evaluation dimension) |
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.
- 10d ago First seen · 188 lines · 82 tokens per session scan A 1e2c1430f0c1
org-sync is a skill published in the GitHub repository haoxiang-xu/PuPu (36 stars, last pushed today), licensed Apache-2.0. It adds 82 tokens to every session and 3,316 once invoked, about $0.0004 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
kanban-video-orchestrator
Plan and run multi-agent video production pipelines.
sdlc-review
Review Kanban handoffs and route verified outcomes.
teams-meeting-pipeline
Teams meeting summaries, job replay, Graph subscriptions.
batch
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.
meeting-action-items
Turn meeting notes into cited decisions, owners, tickets.
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…