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/comisai/comis/market-makingnpx skills add comisai/comis --skill market-makinggit clone --depth 1 https://github.com/comisai/comisWrote 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/comisai/comis/market-making)<a href="https://agentmods.dev/skills/comisai/comis/market-making"><img src="https://agentmods.dev/badge/skills/comisai/comis/market-making.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 | $0.00061 | $0.00778 |
| Opus 5 | $0.00030 | $0.00389 |
| Sonnet 5 | $0.00012 | $0.00156 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade A, and why
mm-sim-desk 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 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.
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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running an algorithmic market-making desk in a simulated market. You quote two-sided prices, take fills, manage your net inventory, and finally settle the session for a graded result. This skill explains how to use the tools — how to actually trade well is your job.
Your tools (mcp:mm-sim/*)
Observe (read-only — read the market and your book):
get_quote— current mid/bid/ask for the symbol and the current episodestep.get_orderbook { levels }— order-book depth (bid/ask sizes) around the mid.get_position— your net inventory, the stated max inventory limit, and your live quote.get_pnl— running PnL plus a risk-adjusted figure (PnL penalized for inventory risk).regime_signals— microstructure diagnostics for the latest window: return autocorrelation, realized volatility (and its trend), and order-flow imbalance. These describe behavior; they do not name a regime.get_fills— the fills you have received so far (each fill moves your inventory).volatility— the realized-volatility series so far (one value per elapsed step).
Act (consequential):
set_strategy { mode }— set your active strategy (a free-textmode). Recorded with the step.post_quote { bid, ask, size }— post a two-sided quote. Advances the market one step; you may receive a fill that changes your inventory.cancel_quote— stand aside. Advances one step with no new fill for you.hedge { qty }— tradeqtyunits (signed) at the current mid to reduce net inventory; a small slippage cost applies. Does not advance the market.settle— close the session and book the result. This returns the graded outcome.
How to run a session
- Read the market first —
get_quote,regime_signals,volatility— and your book withget_position/get_pnl. - Choose and
set_strategy, then work the book withpost_quote(andcancel_quoteto pause). Each of those advances the episode one step; the episode has a fixed number of steps (get_quotereportsstep/totalSteps). - Keep re-reading
regime_signalsas the episode progresses — the market's behavior is not guaranteed to stay the same for the whole episode. - Use
hedgeto keep your net inventory inside the stated limit (get_position.maxInventory). settlewhen you're done to get the graded result.
What ships with it
3 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.
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 · 50 lines · 61 tokens per session scan A 7e5f88f87075
mm-sim-desk is a skill published in the GitHub repository comisai/comis (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 61 tokens to every session and 778 once invoked, about $0.0003 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
loop-orchestration
Reference loop-orchestration example; a local loop host chains governed runx turns through receipts, budgets, context, and stop policy.
org-sync
Use when the CEO wants an organization-wide sync across PuPu's agent teams — running each org's internal sync, then a cross-org sync where departments challenge each other, converging into one decision list. Triggers: "跑一次 org sync", "全局同步", "组织盘点", "/org-sync", "各部门现在什么情况", "有什么要我拍板的".
release-feature-audit
Use when a new PuPu feature finishes implementation and needs its consistency audit before its ticket is marked done — "audit #123", "审计这个功能", "这个 feature 过一遍检查" — or when release-close-sprint roll-call finds a new feature that was never audited. Also covers standalone i18n checks ("漏翻了吗", "检查 i18n"), which used to be…
growth-analyst
Use when analyzing PuPu's open-source growth or health for the founder — GitHub traffic, downloads/installs, releases, community, or contributor activity — or when producing a growth report or weekly COO report. Repo is haoxiang-xu/PuPu. Triggers: "how is PuPu growing?", "are people installing PuPu?", "which release…
test-api
Use when running QA / regression tests against PuPu, when verifying a code change actually works in the running app, or when reading PuPu UI/state without screenshotting manually. Triggers on tasks like "test that PuPu still creates chats correctly", "verify the new model selector works end-to-end", "send a message…
gitnexus-debugging
Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: "Why is X failing?", "Where does this error come from?", "Trace this bug".