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 order-exception-to-resolutiongit 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/order-exception-to-resolution)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/order-exception-to-resolution"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/order-exception-to-resolution/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/order-exception-to-resolution"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/order-exception-to-resolution.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 | $0.00032 | $0.00707 |
| Opus 5.5 | $0.00013 | $0.00283 |
| Sonnet 5.5 | $0.00006 | $0.00141 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
order-exception-to-resolution 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.
Order Exception to Resolution
Outcome
Produce a sourced order exception, a policy and money review, an unsent customer draft, and proof of any approved resolution. A customer request, Shopify Return, owner approval, refund transaction, and delivered reply are separate states.
When to use
Use for an order or fulfillment problem tied to a return or refund request. One compatible Crew may fill both slots with separate validated outputs.
Discovery and user direction
Inspect existing Crews, store access, fulfillment and payment sources, helpdesk case, policy, owners, and prior actions. Propose reuse or creation and show the plan before Builder applies it. Installation only copies this guide and pending SETUP.json.
Required inputs
Confirm exact store, order, customer, case, affected line IDs, currency, policy version, observation window, approval owner, and contact rule. An authorized export supports a manual read-only route.
Plan and AgentWorks tools
Reuse or propose Store Operations Coordinator and Returns & Refunds Coordinator. Builder may use create_crew with stable keys for missing Crews. Route Store Operations' store-order-exception/v1 to Returns only after scripts/validate_handoff.py --order-only <order.json> passes. Returns re-reads current payment, refund, dispute, fulfillment, Shopify Return, and helpdesk state and emits return-resolution-review/v1. Validate both artifacts before owner review. Only a fulfilled affected item may take the Shopify Return route; an unfulfilled item needs a reviewed order-edit, cancellation, or refund route.
Knowledge and persistence
Save store, order, line, customer, case, action, approval, transaction, return, and ticket IDs; source times; policy version; chosen route; receipts; and next check. Re-read current state before every repeat or money action.
Validation and reporting
Run the handoff validator on real bounded artifacts. The valid order and review are fictional; the invalid review must fail. The reporting dashboard shows prepared, pending approval, executed, verified, and blocked cases with source links and run cost. A validator checks structure, not source truth.
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.
- examples/invalid-return-resolution-review.json 823 B
- examples/return-resolution-review.json 1.2 KB
- examples/store-order-exception.json 1.0 KB
- playbook.json 4.7 KB
- references/team-and-handoffs.md 3.3 KB
- scripts/test_validate_handoff.py 4.1 KB runs code
- scripts/validate_handoff.py 6.7 KB runs code
- SETUP.json 3.4 KB
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 · 32 tokens per session scan A 120de15d04a2
order-exception-to-resolution is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 32 tokens to every session and 707 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
goga-cell-go
Golang rules for implementing CODEMANIFEST contracts.
cross-border-ecommerce
Skill "cross-border-ecommerce" from aimerdoux/wavex-os, covering marketing cross-border e-commerce specialist, your identity & memory, core mission, cross-border platform operations and international logistics & overseas warehousing.
livestream-commerce-coach
Skill "livestream-commerce-coach" from aimerdoux/wavex-os, covering marketing livestream commerce coach, your identity & memory, core mission, host talent development and livestream script system.
china-ecommerce-operator
A guide for running marketing and sales on Chinese e-commerce platforms, including live-streamed shopping.
kuaishou-strategist
Skill "kuaishou-strategist" from aimerdoux/wavex-os, covering marketing kuaishou strategist, 🧠 your identity & memory, 🎯 your core mission, master kuaishou's distinct platform identity and drive live commerce excellence.
agency-china-e-commerce-operator
Expert China e-commerce operations specialist covering Taobao, Tmall, Pinduoduo, and JD ecosystems with deep expertise in product listing optimization, live commerce, store operations, 618/Double 11 campaigns, and cross-platform strategy.