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/okx/plugin-store/gmx-v2-pluginnpx skills add okx/plugin-store --skill gmx-v2-plugingit clone --depth 1 https://github.com/okx/plugin-storeWhat 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 | $0.00094 | $0.07998 |
| Opus 5 | $0.00047 | $0.03999 |
| Sonnet 5 | $0.00019 | $0.01600 |
| Haiku 4.5 | $0.00009 | $0.00800 |
Grade C, and why
gmx-v2-plugin scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$ONCHAINOS_TMP" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
REMOTE_VER=$(curl -sf --max-time 3 "https://raw.githubusercontent.com/okx/plugin-store/main/skills/gmx-v2-plugin/plugin.yaml" | grep '^version' | head -1 | tr -d '"' | awk '{print $2}') How it starts
The opening of the file, as written. The whole thing — 652 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-flight Dependencies (auto-injected by Plugin Store CI)
Run once per session before first use. These checks ensure required tools are installed.
Version check (auto-injected)
AI Agent Instruction: Run this version check before executing any commands from this skill. If an update is applied, re-read this SKILL.md before proceeding — the instructions may have changed.
# Check for skill updates (1-hour cache)
UPDATE_CACHE="$HOME/.plugin-store/update-cache/gmx-v2-plugin"
CACHE_MAX=3600
LOCAL_VER="0.2.7"
DO_CHECK=true
if [ -f "$UPDATE_CACHE" ]; then
CACHE_MOD=$(stat -f %m "$UPDATE_CACHE" 2>/dev/null || stat -c %Y "$UPDATE_CACHE" 2>/dev/null || echo 0)
NOW=$(date +%s)
AGE=$(( NOW - CACHE_MOD ))
[ "$AGE" -lt "$CACHE_MAX" ] && DO_CHECK=false
fi
if [ "$DO_CHECK" = true ]; then
REMOTE_VER=$(curl -sf --max-time 3 "https://raw.githubusercontent.com/okx/plugin-store/main/skills/gmx-v2-plugin/plugin.yaml" | grep '^version' | head -1 | tr -d '"' | awk '{print $2}')
if [ -n "$REMOTE_VER" ]; then
mkdir -p "$HOME/.plugin-store/update-cache"
echo "$REMOTE_VER" > "$UPDATE_CACHE"
fi
fi
REMOTE_VER=$(cat "$UPDATE_CACHE" 2>/dev/null || echo "$LOCAL_VER")
if [ "$REMOTE_VER" != "$LOCAL_VER" ]; then
echo "Update available: gmx-v2-plugin v$LOCAL_VER -> v$REMOTE_VER. Updating..."
npx skills add okx/plugin-store --skill gmx-v2-plugin --yes --global 2>/dev/null || true
echo "Updated gmx-v2-plugin to v$REMOTE_VER. Please re-read this SKILL.md."
fi
Install onchainos CLI + Skills (auto-injected)
# 1. Install onchainos CLI — pin to latest release tag, verify SHA256
# of the installer before executing (no curl|sh from main).
if ! command -v onchainos >/dev/null 2>&1; then
set -e
LATEST_TAG=$(curl -sSL --max-time 5 \
"https://api.github.com/repos/okx/onchainos-skills/releases/latest" \
| sed -n 's/.*"tag_name"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/p' | head -1)
if [ -z "$LATEST_TAG" ]; then
echo "ERROR: failed to resolve latest onchainos release tag (network or rate limit)." >&2
echo " Manual install: https://github.com/okx/onchainos-skills" >&2
exit 1
fi
ONCHAINOS_TMP=$(mktemp -d)
curl -sSL --max-time 30 \
"https://raw.githubusercontent.com/okx/onchainos-skills/${LATEST_TAG}/install.sh" \
-o "$ONCHAINOS_TMP/install.sh"
curl -sSL --max-time 30 \
"https://github.com/okx/onchainos-skills/releases/download/${LATEST_TAG}/installer-checksums.txt" \
-o "$ONCHAINOS_TMP/installer-checksums.txt"
EXPECTED=$(awk '$2 ~ /install\.sh$/ {print $1; exit}' "$ONCHAINOS_TMP/installer-checksums.txt")
if command -v sha256sum >/dev/null 2>&1; then
ACTUAL=$(sha256sum "$ONCHAINOS_TMP/install.sh" | awk '{print $1}')
else
ACTUAL=$(shasum -a 256 "$ONCHAINOS_TMP/install.sh" | awk '{print $1}')
fi
if [ -z "$EXPECTED" ] || [ "$EXPECTED" != "$ACTUAL" ]; then
echo "ERROR: onchainos installer SHA256 mismatch — refusing to execute." >&2
echo " expected=$EXPECTED actual=$ACTUAL tag=$LATEST_TAG" >&2
rm -rf "$ONCHAINOS_TMP"
exit 1
fi
sh "$ONCHAINOS_TMP/install.sh"
rm -rf "$ONCHAINOS_TMP"
set +e
fi
# 2. Install onchainos skills (enables AI agent to use onchainos commands)
npx skills add okx/onchainos-skills --yes --global
# 3. Install plugin-store skills (enables plugin discovery and management)
npx skills add okx/plugin-store --skill plugin-store --yes --global
What ships with it
26 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.
- .claude-plugin/plugin.json 531 B
- .gitignore 8 B
- Cargo.lock 78 KB
- Cargo.toml 436 B
- LICENSE 1.0 KB
- plugin.yaml 708 B
- src/abi.rs 19 KB
- src/api.rs 11 KB
- src/commands/cancel_order.rs 3.0 KB
- src/commands/claim_funding_fees.rs 4.2 KB
- src/commands/close_position.rs 8.2 KB
- src/commands/deposit_liquidity.rs 11 KB
- src/commands/get_orders.rs 10 KB
- src/commands/get_positions.rs 7.5 KB
- src/commands/get_prices.rs 2.7 KB
- src/commands/list_markets.rs 3.2 KB
- src/commands/mod.rs 278 B
- src/commands/open_position.rs 13 KB
- src/commands/place_order.rs 12 KB
- src/commands/quickstart.rs 7.3 KB
- src/commands/withdraw_liquidity.rs 6.8 KB
- src/config.rs 2.4 KB
- src/main.rs 3.8 KB
- src/onchainos.rs 8.4 KB
- src/rpc.rs 3.7 KB
- SUMMARY.md 1.9 KB
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.
- 2d ago First seen · 652 lines · 94 tokens per session scan C 5fdba5831f6c
gmx-v2-plugin is a skill published in the GitHub repository okx/plugin-store (11 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 7,998 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, 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
credit-analysis
固收与信用分析:信用债评级、利差分析、违约风险评估、城投债研究、可转债定价与策略。.
geopolitical-risk
Geopolitical risk analysis: quantify crisis signals, identify precursors, and build event-driven strategies for war, sanctions, and supply disruption scenarios.
vibe-trading
Professional finance research toolkit — backtesting (10 engines + benchmark comparison panel), factor analysis, Alpha Zoo (462 pre-built alphas across qlib158/alpha101/gtja191/academic/fundamental), options pricing, 90 finance skills, 30 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract →…
correlation-regime
Correlation-regime detection and crisis attribution — edge-density regime states with hysteresis, causal (no look-ahead) smoothing, regime-aware exposure context, first-mover crisis attribution with honest NAME / MACRO / AMBIGUOUS / ABSTAIN verdicts, and a correlation-rewiring leaderboard that catches slow bleed-outs.
adr-hshare
ADR/H-share/A-share cross-listing premium analysis — track pricing gaps between US-listed ADRs, HK-listed H-shares, and A-shares for arbitrage signals, dual-listing valuation, and delisting risk assessment.
behavioral-finance
Behavioral finance applications: theories of overreaction and underreaction, behavioral explanations for momentum and reversal, investor sentiment cycles, cognitive-bias checklists, and debiasing quantitative strategies.