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 agentmods add skills/genvjacobc/lightspeed-x-mcp/setupnpx skills add genvjacobc/lightspeed-x-mcp --skill setupgit 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/setup)<a href="https://agentmods.dev/skills/genvjacobc/lightspeed-x-mcp/setup"><img src="https://agentmods.dev/badge/skills/genvjacobc/lightspeed-x-mcp/setup.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 | $0.00076 | $0.01456 |
| Opus 5 | $0.00038 | $0.00728 |
| Sonnet 5 | $0.00015 | $0.00291 |
| Haiku 4.5 | $0.00008 | $0.00146 |
Grade B, and why
setup scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat > "$HOME/.claude/plugins/data/lightspeed-x-lightspeed-x-mcp/credentials.env" <<'ENVEOF' How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connect Lightspeed X
You do the work. Do not hand the user a list of commands to run.
You have a Bash tool. Every install step here is a shell command you can run yourself. The only thing the user does is copy their token out of Lightspeed and paste it into a text file, because a token must never enter the chat.
If you catch yourself writing "run this command," stop and run it instead.
The one rule about the token
Never ask the user to paste their token into the chat. Not into a prompt, not to confirm it, not to check it. It would land in the transcript.
They paste it into a file in Notepad. You never see it. You verify by calling the API, not by reading the value.
If they paste a token in chat anyway, tell them plainly that it is now in the transcript, that they should revoke it in Lightspeed and create a new one, then continue with the new one.
Step 1: check what state you are in
Call lightspeed_setup_status.
| Result | Go to |
|---|---|
| Reports connected | Step 5. Just prove it works. |
| Reports not connected, gives a path | Step 3, using that path |
| Tool does not exist at all | Step 2. The plugin is not installed. |
Never guess the credential file path. The tool reports the real one, and it differs by platform and by how the server was installed.
Step 2: install the plugin, yourself
Only needed if the tools are missing entirely. Run these with Bash. They are shell commands, not slash commands, so you can execute them:
claude plugin marketplace add genvjacobc/lightspeed-x-mcp
claude plugin install lightspeed-x@lightspeed-x-mcp --scope user
Expected: "Successfully added marketplace" then "Successfully installed plugin." "already installed" or "already added" is fine, keep going.
If claude is not found, Claude Code is not on PATH for the shell. On Windows
try "$LOCALAPPDATA/Programs/claude/claude.exe", or tell the user to update
Claude Code.
A shell install does not load into the running session. Continue to Step 3 and have them restart at the end; do not stop here.
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.
- 4d ago First seen · 140 lines · 76 tokens per session scan B 5f80a9e483ce
setup is a skill published in the GitHub repository genvjacobc/lightspeed-x-mcp (0 stars, last pushed 9d ago), licensed MIT. It adds 76 tokens to every session and 1,456 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
client-scripts
Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.
agoragentic-transaction-assurance
Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority. Use when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation; handle paid retries safely; or prepare an authority request for owner…
debugging-mutations
Verify what changed on a ServiceNow instance after a tool call — sysaudit inspection, syslog/transaction logs, session context, Flow Designer execution logs, outbound HTTP traces.
maya-shot-export
Pipeline stage — shot-level export: frame ranges, cameras, FBX / Alembic packaging for editorial. Use when packaging shot data for downstream departments. Not for full pipeline publish (maya-pipeline) or scene assembly (maya-scene-assembly).
social-scrape
Collect public posts and discussion from X, LinkedIn and Hacker News through a local signed-out browser, then report them in chat or write them to a document. Use when the user wants to scrape, monitor or research specific accounts, topics, hashtags or discussions on social platforms.