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 genvjacobc/lightspeed-x-mcp --skill customizegit clone --depth 1 https://github.com/genvjacobc/lightspeed-x-mcpWrote 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/genvjacobc/lightspeed-x-mcp/customize)<a href="https://agentmods.dev/skills/genvjacobc/lightspeed-x-mcp/customize"><img src="https://agentmods.dev/badge/skills/genvjacobc/lightspeed-x-mcp/customize.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 5.1 | $0.00105 | $0.01200 |
| Opus 5 | $0.00053 | $0.00600 |
| Sonnet 5 | $0.00021 | $0.00240 |
| Haiku 4.5 | $0.00011 | $0.00120 |
Grade A, and why
customize 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 6d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Change how reports behave
You do the work. Read the current settings, make the change, show what you changed. Do not hand the user a file path and a schema and ask them to edit YAML.
Settings take effect on the next tool call. No restart, no reload.
What you are editing
One file: config.yaml, in the same directory as their credentials.
lightspeed_get_config reports the exact path. It holds no credentials, so you
can read it, quote it, and rewrite it freely.
Never touch credentials.env. Different file, same directory, and the only
one with a secret in it. If a customization request seems to need the token,
you have misread the request.
The loop
1. Read before writing. Call lightspeed_get_config. It returns every
effective setting, whether each came from the file or a default, and any
warnings. If no file exists yet, call it again with include_template: true to
get a commented starter rather than inventing the schema.
2. Resolve anything the user said in words. They will say "my stores" and
"the Omaha ones", not UUIDs. Call lightspeed_list_outlets and match names
yourself. Write UUIDs to the file, not names: a name that gets edited in
Lightspeed silently stops matching, and a UUID does not.
Read back the store names you resolved and get agreement before writing. Scope is the setting most likely to make later numbers look wrong, so it is the one worth confirming.
3. Back up, then write. Copy the existing file to config.yaml.bak first.
There is one file and no history behind it.
Preserve comments and any settings you are not changing. Rewriting the whole file from the template because it was easier than editing two lines throws away work the user did.
4. Verify by reading, not by asserting. Call lightspeed_get_config again.
Check the values changed, the From column now says file, the store scope
resolved to the right names, and no new warnings appeared. Then show the user
what changed, in their words.
What is adjustable
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.
- 6d ago First seen · 109 lines · 105 tokens per session scan A 827c7c8a2527
customize is a skill published in the GitHub repository genvjacobc/lightspeed-x-mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 105 tokens to every session and 1,200 once invoked, about $0.0005 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
find-contact
A contact and company lookup for amoCRM, a customer-management system. It searches existing records, checks for duplicates, and can create a new contact or company with notes and related activity.
pipeline-report
A procedure for reporting the state of an amoCRM sales funnel, a set of stages that deals move through before they are won or lost. It groups deals by stage and value and checks how long they have been inactive.
change-tracking
A change-tracking workflow for a 1C database, a business accounting and records system. It retrieves records changed after a saved time marker, including document details and document line items.
inbox-triage
A procedure for reviewing unread Avito chats and connecting each conversation to its listing. Avito is an online marketplace where people buy and sell items.
complete-task
A workflow for completing or reassigning ELMA365 business-process tasks. ELMA365 is a business process management system in which tasks move a process from one step to the next.
gigachat-embeddings
A text-embedding workflow for GigaChat. Embeddings are numeric representations that let software compare meanings rather than only matching exact words.