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 refund-request-to-reconciled-outcomegit 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/refund-request-to-reconciled-outcome)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/refund-request-to-reconciled-outcome"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/refund-request-to-reconciled-outcome/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/refund-request-to-reconciled-outcome"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/refund-request-to-reconciled-outcome.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 | $0.00026 | $0.00739 |
| Opus 5.5 | $0.00010 | $0.00296 |
| Sonnet 5.5 | $0.00005 | $0.00148 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
refund-request-to-reconciled-outcome 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refund Request to Reconciled Outcome
Outcome
Take one customer refund request from exact payment and policy review to a finance impact record. The first result is a reviewed proposal; an actual refund is an optional, separately approved action. If no refund has happened, the finance result must say pending, denied, or blocked rather than reconciled.
When to use
Use for a SaaS customer refund where support, billing and finance records must agree. Billing Operations Coordinator holds the Refund Review pack; Revenue & Close Analyst owns the ledger treatment. Reuse compatible Crews. Split identities when money permissions, owner, or independent review require it.
Discovery and user direction
Inspect existing Crews, exact provider account and mode, customer request, payment, prior refunds, refund policy, finance source, and owners. Ask for missing facts and show a concrete plan before Builder configures anything. A customer request does not authorize a provider write or customer message.
Required inputs
Bind entity, customer, request ID, charge or payment ID, provider account and mode, currency, original amount, previous and pending refunds, requested amount, policy version, billing reviewer, finance owner, and authoritative ledger or export. Preserve unknowns and conflicting sources.
Plan and AgentWorks tools
Create steps for Billing review, blocking validation, and Finance review. Billing emits refund-decision/v1 with exact minor-unit arithmetic and an owner decision. Validate it before handing it to Revenue & Close. Finance re-reads the payment, refund and ledger sources and emits refund-reconciliation/v1. An optional approved refund action sits between reviews, with exact payment, amount, reason, idempotency key, current-state recheck, and provider receipt. A draft reply or approval alone never becomes a refund or ledger posting.
Knowledge and persistence
Keep stable request, payment, refund and customer IDs; provider account and mode; policy revision; amounts and currency; source observation times; owner decisions; action keys and receipts; ledger references; and next review. On repeat, re-read payment and refund state before proposing another action.
What ships with it
8 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 · 48 lines · 26 tokens per session scan A b3e666e911d2
refund-request-to-reconciled-outcome is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 26 tokens to every session and 739 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.