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 checkout-signal-to-reviewed-recoverygit 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/checkout-signal-to-reviewed-recovery)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/checkout-signal-to-reviewed-recovery"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/checkout-signal-to-reviewed-recovery/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/checkout-signal-to-reviewed-recovery"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/checkout-signal-to-reviewed-recovery.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 | $0.00029 | $0.00728 |
| Opus 5.5 | $0.00012 | $0.00291 |
| Sonnet 5.5 | $0.00006 | $0.00146 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
checkout-signal-to-reviewed-recovery 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.
Checkout Signal to Reviewed Recovery
Outcome
For one checkout and channel, produce a current, source-linked decision: suppress, ask for missing evidence, or prepare an unsent recovery draft for merchant review. Count a later message or order only from separate provider and linked-order evidence.
When to use
Use for a merchant-owned abandoned checkout recovery queue. Do not use for payment capture, order returns, or a general storefront conversion audit. One artifact pair covers one checkout, campaign, and channel.
Discovery and user direction
Inspect current Shopify Messaging or other recovery automations first. Ask the merchant which channel and policy apply, whether another provider owns the send, who approves contact, and whether read-only review is the whole job. Propose reuse or creation of the two Crews and show the route before Builder applies it.
Required inputs
Bind store, market, checkout, campaign, channel, merchant policy version, owner, current checkout and linked-order source, consent/opt-out source, and prior-send history. Missing customer access or contact policy yields an unknown or suppressed decision, not a send.
Plan and AgentWorks tools
Shopify Growth Analyst emits a minimal checkout-recovery-signal/v1 with exact identity, observation and hypothesis, excluding contact details. Validate it using scripts/validate_handoff.py --signal-only <signal.json>. Checkout Recovery Coordinator re-reads the same checkout, completion/order, consent and message history, then emits checkout-recovery-review/v1; validate the pair before any owner review. Keep a separate approved action route for a send. A webhook is a prompt to re-read, with verified delivery and idempotency, never an instruction to contact.
Knowledge and persistence
Save stable checkout-channel-campaign case and action IDs, source times, policy version, suppression reason, owner decision, prior provider attempts, approval, and send receipt. Store contact details only in the authorized provider, not the shared dashboard. Re-read state before every repeated decision.
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/checkout-recovery-review.json 1.8 KB
- examples/checkout-recovery-signal.json 481 B
- examples/invalid-checkout-recovery-review.json 1.0 KB
- playbook.json 4.5 KB
- references/team-and-handoffs.md 4.1 KB
- scripts/test_validate_handoff.py 4.3 KB runs code
- scripts/validate_handoff.py 8.7 KB runs code
- SETUP.json 2.6 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 · 29 tokens per session scan A 0040d068e5a5
checkout-signal-to-reviewed-recovery is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 29 tokens to every session and 728 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.