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.
git clone --depth 1 https://github.com/iamgoatedaf/lighter-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/commands/iamgoatedaf/lighter-mcp/lighter-kill)<a href="https://agentmods.dev/commands/iamgoatedaf/lighter-mcp/lighter-kill"><img src="https://agentmods.dev/badge/commands/iamgoatedaf/lighter-mcp/lighter-kill.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 | $0.00024 | $0.00430 |
| Opus 5 | $0.00012 | $0.00215 |
| Sonnet 5 | $0.00005 | $0.00086 |
| Haiku 4.5 | $0.00002 | $0.00043 |
Grade A, and why
lighter-kill 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 8d 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.
What it actually says
/lighter-kill
You are about to flatten the user's entire Lighter account. This is a high-risk command. Treat every step as irreversible.
Steps:
- Call
lighter_safety_status. Ifmodeis notliveorfunds, stop and tell the user the account is in{mode}so there is nothing live to kill. Do not proceed. - Call
lighter_orders_openandlighter_account_infoso you can describe exactly what will be cancelled and flattened. - Call
lighter_live_cancel_allwithout aconfirmation_id. You will get a preview envelope withconfirmation_id. - Call
lighter_live_close_allwithout aconfirmation_id. Usewith_cancel_all = trueand a conservativeslippage(default 0.01). You will get a second preview envelope with its ownconfirmation_id. - Show the user a single combined plan:
- "Will cancel N open orders" (list them).
- "Will flatten M open positions" (list them with side/size).
- Estimated slippage budget.
- Both confirmation_ids and their expiries.
- Wait for the user to type the word "confirm" (or equivalent in their language). Do not accept "yes", "ok", or "go" — require an explicit confirmation word so it cannot be triggered by accidental autocomplete.
- On confirmation, call both tools again with the same arguments plus
their respective
confirmation_ids. Order: cancel_all first, then close_all. - Render the final result: how many orders cancelled, how many positions closed, any errors verbatim.
If any preview returns category: "safety", surface the error and stop.
If the user types anything other than the explicit confirmation word, abort.
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.
- 8d ago First seen · 39 lines · 24 tokens per session scan A 91fac3073490
lighter-kill is a command published in the GitHub repository iamgoatedaf/lighter-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 430 once invoked, about $0.0001 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 commands, from other repositories
search-flights
Search award flight availability across airlines.
usage-report
Generate a comprehensive team usage and spending report for the current billing cycle.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.