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 runesleo/polymarket-toolkit --skill polymarket-pnlgit clone --depth 1 https://github.com/runesleo/polymarket-toolkitWrote 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/runesleo/polymarket-toolkit/polymarket-pnl)<a href="https://agentmods.dev/skills/runesleo/polymarket-toolkit/polymarket-pnl"><img src="https://agentmods.dev/badge/skills/runesleo/polymarket-toolkit/polymarket-pnl/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/runesleo/polymarket-toolkit/polymarket-pnl"><img src="https://agentmods.dev/badge/skills/runesleo/polymarket-toolkit/polymarket-pnl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Supply Chain · line 91 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 | $0.00077 | $0.01675 |
| Opus 5 | $0.00039 | $0.00838 |
| Sonnet 5 | $0.00015 | $0.00335 |
| Haiku 4.5 | $0.00008 | $0.00168 |
Grade A, and why
polymarket-pnl scanned grade A 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
If the user just wants a quick profile (win rate, positions, category breakdown), use the `polymarket-profile` skill instead — it's lighter and runs on curl alone. How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Polymarket Precise PnL
Compute precise, audit-grade PnL for any Polymarket address via the Data API cashflow method. Unlike position-level approximations used by most profilers, this reconstructs every BUY / SELL / REDEEM / MERGE / SPLIT / REBATE event and reconciles against current unrealized position value.
Validated against Polymarket's official /profit endpoint on the public leaderboard: MAPE ~0.2%, all top accounts within 1% error.
Trigger
Invoke this skill when the user wants:
- Audit-grade PnL for one or more Polymarket addresses
- Bulk PnL over a leaderboard or an address list
- Benchmark mode: compare a local PnL dataset vs. the official /profit values
If the user just wants a quick profile (win rate, positions, category breakdown), use the polymarket-profile skill instead — it's lighter and runs on curl alone.
Requirements
python3(3.9+)- One Python package:
httpx
Install once:
pip install -r ${SKILL_DIR}/requirements.txt
# or
pip install httpx
${SKILL_DIR} is the path where this skill lives (for example, /path/to/your/agent/skills/polymarket-pnl/).
Core CLI
All invocations run from the skill directory (or with python3 <skill_dir>/compute_precise_pnl.py):
# Single address
python3 compute_precise_pnl.py --address 0x63ce342161250d705dc0b16df89036c8e5f9ba9a
# Bulk: top N on the leaderboard (auto-fetched)
python3 compute_precise_pnl.py --leaderboard 50
# Address list from a text file (one 0x per line, `#` for comments)
python3 compute_precise_pnl.py --addresses-file targets.txt
# Benchmark: compare your local PnL JSONL against the recomputed precise PnL
python3 compute_precise_pnl.py --leaderboard 100 \
--benchmark local_pnl.jsonl \
-o precise_vs_local.jsonl
Output is JSONL streamed to --output (default: ./precise_pnl.jsonl).
Output schema
Each line is one address record:
| Field | Type | Meaning |
|---|---|---|
address |
str | The lowercase 0x proxy wallet |
pnl |
float | Trading cashflow PnL (BUY/SELL/REDEEM/MERGE/SPLIT/REBATE + unrealized). Primary metric. |
pnl_inclusive |
float | pnl + REWARD + REFERRAL_REWARD + CONVERSION (platform credits) |
total_buy, total_sell, total_redeem, total_merge, total_split, total_rebate, total_reward, total_referral, total_conversion |
float | Sum of each activity type |
unrealized |
float | Current mark-to-market value of open positions |
open_positions |
int | Number of open positions |
trade_count |
int | Total BUY + SELL events |
computed_at |
int | Unix seconds when record was produced |
complete |
bool | True if every paginated activity call returned fully |
pagination_incomplete |
bool | True if the Data API's ~10k offset ceiling was hit for at least one activity type |
pagination_incomplete_types |
list[str] | None | Which activity types hit the ceiling ("BUY", "SELL", ...) |
What ships with it
5 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.
- 9d ago First seen · 128 lines · 77 tokens per session scan A 772d3d790386
polymarket-pnl is a skill published in the GitHub repository runesleo/polymarket-toolkit (193 stars, last pushed 20d ago), licensed MIT. It adds 77 tokens to every session and 1,675 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
polymarket
Query Polymarket prediction market data — search markets, get prices, orderbooks, and price history. Read-only via public REST APIs, no API key needed.
polymarket
Query Polymarket: markets, prices, orderbooks, history.
polymarket
Query Polymarket: markets, prices, orderbooks, history.
quotient
Prediction-market intelligence for Polymarket agents. Quotient runs a multi-role AI forecasting pipeline over 1,600+ sources and publishes daily trade signals with side, entry prices, conviction tiers, capacity, and convergence reads. Pull forecasts (with what-changed deltas), recent sources (articles + X posts), the…
moonpay-scout
Prediction market arbitrage & alpha scout. Searches Polymarket and Kalshi for the same event, runs cross-platform arb math (including fees), and ranks opportunities by profitability. Use when asked to "find arb", "scout markets", "find edge", or scan a specific topic across prediction markets.
polymarket
Query Polymarket prediction market data — search markets, get prices, orderbooks, and price history. Read-only via public REST APIs, no API key needed.