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/breadchaincoop/labor.fun/safe-payoutnpx skills add BreadchainCoop/labor.fun --skill safe-payoutgit clone --depth 1 https://github.com/BreadchainCoop/labor.funWrote 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/breadchaincoop/labor.fun/safe-payout)<a href="https://agentmods.dev/skills/breadchaincoop/labor.fun/safe-payout"><img src="https://agentmods.dev/badge/skills/breadchaincoop/labor.fun/safe-payout.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 | $0.00043 | $0.00539 |
| Opus 5 | $0.00022 | $0.00269 |
| Sonnet 5 | $0.00009 | $0.00108 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
safe-payout 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 4d 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
Safe Payout (on-chain reimbursement)
You can propose a token reimbursement from the cooperative's Safe{Wallet}
multisig with the request_safe_payout tool. Read this before using it.
You are a proposer, never an approver
- The tool only drafts a proposal. The payout happens only when the Safe's signers reach their threshold in their own wallets. You cannot confirm or execute — and you must never imply otherwise.
- Never say a payout is "done", "sent", or "paid" until the chain confirms it.
Until then it is proposed / N-of-threshold confirmed. The
safe-payoutsflow posts those mirror updates automatically — you don't poll. - There are no approval tiers and no amount limits you enforce. Whether it pays is the signers' on-chain decision, not yours. Don't gate or editorialize.
Fiat vs crypto
- Crypto/token reimbursement (BREAD, on-chain) →
request_safe_payout. - Fiat expense (USD, receipts, venmo/zelle/etc.) →
request_expense(the expense-helper skill). Don't cross them.
Recipient address
- Prefer
recipient_slug(a KB people slug) — the wallet address is read from that member's profile (address:frontmatter). - If their profile has no address, or you only have a raw address you can't verify, ask the member for a checksummed wallet address. Never guess or reuse an address from elsewhere — a wrong address means lost funds.
- Only pass
recipient_addressdirectly when the member has just given you a checksummed0x…address in the conversation.
Amount
- Pass the human token amount as a string in
amount(e.g."100","0.5") — not base units/wei. The orchestrator converts using the token's decimals from config.
After you file it
Tell the member it's been proposed and that it pays out once signers confirm in
their wallets. The flow will post the Safe{Wallet} link and the running
confirmation count to the channel. See rules/finance/safe-payouts.md.
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.
- 4d ago First seen · 50 lines · 43 tokens per session scan A fca6d3aefdb0
safe-payout is a skill published in the GitHub repository BreadchainCoop/labor.fun (2 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 539 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 2026-08-31.
Other skills, from other repositories
cobie-cycle-filter
Use when evaluating crypto decisions through a Cobie-style cycle filter: common-sense risk, narrative traps, leverage humility, and avoiding obvious stupid trades.
hyperliquid
Hyperliquid L1 perps DEX (69% market share).
bridge
Cross-chain token transfers using Wormhole and CCTP.
portfolio
Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction. Activates when the user pastes a wallet address or asks about yield/positions/rebalancing. Bootstraps a per-user "portfolio" project, aggregates positions across all the user's addresses inside one project, and offers a…
marginfi
MarginFi — Solana lending and borrowing.
copy-trading
Wallet evaluation, monitoring, and copy-trade strategy design for Solana DEX trading.