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 manishiitg/coding-agent-loop --skill spend-payables-coordinatorgit clone --depth 1 https://github.com/manishiitg/coding-agent-loopWrote 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/manishiitg/coding-agent-loop/spend-payables-coordinator)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/spend-payables-coordinator"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/spend-payables-coordinator/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/manishiitg/coding-agent-loop/spend-payables-coordinator"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/spend-payables-coordinator.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 | $0.00030 | $0.01184 |
| Opus 5.5 | $0.00012 | $0.00474 |
| Sonnet 5.5 | $0.00006 | $0.00237 |
| Haiku 4.5 | $0.00003 | $0.00118 |
Grade A, and why
spend-payables-coordinator 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 20d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spend & Payables Coordinator
Use this skill to organize what the business owes and what it has spent. It is a separate Crew when vendor, card, or payment permissions differ from finance analysis. It may also be a supporting capability in a Crew with the same approved owner and access.
Setup in chat
Read templates/spend-payables-coordinator/TEMPLATE_SETUP.json and SETUP.md. Verify each check with the owner before adding its ID to completed_steps. Preserve existing progress and an existing primary Crew identity. Chat-only or no-recurrence is a valid completed decision for optional checks. Report verified work, exceptions, and the next pending check.
Produce the first payables queue
- Confirm entity, period, currency, vendor owner, bill approval and payment policy, budget owners, and duplicate criteria. Obtain authorized bill, card, expense, or vendor exports; a live connection is optional. Identify which system is authoritative for bill status and whether payment is already scheduled.
- Extract bill ID, vendor identity, invoice number, invoice date, due date, amount, currency, tax fields present, PO/contract reference, receipt, category, approval status, and payment status. Preserve the original document and source link. Treat a receipt, card transaction, and vendor invoice as different records until matched.
- Check exact and near duplicates using vendor, invoice number, amount, currency, dates, and document evidence. Check credits, partial payments, recurring subscriptions, missing receipts or POs, unusual amounts, policy limits, and expenses coded to the wrong period. Flag uncertainty rather than accusing a vendor or employee.
- Produce a queue with one row per bill or exception: source IDs, due date, amount/currency, approval owner, current state, policy reason, proposed next step, and evidence gap. Separate ready for owner review, needs more evidence, and already paid/scheduled. Do not represent an uncoded bill as an approved payment.
- Summarize spend by vendor/category and compare to a supplied budget only when periods and definitions match. Ask the owner to review sample matches, classifications, and priorities before completing setup.
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.
- 20d ago First seen · 43 lines · 30 tokens per session scan A a9cd0405e818
spend-payables-coordinator is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 30 tokens to every session and 1,184 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-27.
Other skills, from other repositories
gridcraft
Headless spreadsheets with GridCraft (XLSX/CSV/TSV workbooks, formula evaluation, recalculation, PDF export), provisioned on demand by pi-craft. Use for "build a budget spreadsheet with formulas", "convert this xlsx to csv", "what does this formula evaluate to", "change a cell and recalculate the totals", "export the…
goga-cell-go
Golang rules for implementing CODEMANIFEST contracts.
loan-officer-assistant
Skill "loan-officer-assistant" from aimerdoux/wavex-os, covering 🏦 loan officer assistant agent, 🧠 your identity & memory, 🎯 your core mission, 🚨 critical rules you must follow and 📋 your technical deliverables.
finance-tracker
Skill "finance-tracker" from aimerdoux/wavex-os, covering finance tracker agent personality, 🧠 your identity & memory, 🎯 your core mission, maintain financial health and performance and enable strategic financial decision making.
bookkeeper
Skill "bookkeeper" from aimerdoux/wavex-os, covering 📒 bookkeeper & controller agent, 🧠 your identity & memory, 🎯 your core mission, 🚨 critical rules you must follow and 📋 your technical deliverables.
financial-analyst
Skill "financial-analyst" from aimerdoux/wavex-os, covering 📊 financial analyst agent, 🧠 your identity & memory, 🎯 your core mission, 🚨 critical rules you must follow and 📋 your technical deliverables.