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/nunchi-trade/agent-cli/guardnpx skills add Nunchi-trade/agent-cli --skill guardgit clone --depth 1 https://github.com/Nunchi-trade/agent-cliWhat 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 | $0.00095 | $0.02063 |
| Opus 5 | $0.00048 | $0.01032 |
| Sonnet 5 | $0.00019 | $0.00413 |
| Haiku 4.5 | $0.00010 | $0.00206 |
Grade A, and why
guard-trailing-stop 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 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.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- guard-trailing-stop — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guard Trailing Stop
Two-phase ROE-based trailing stop that protects profits on Hyperliquid perp positions.
How It Works
Phase 1: "Let It Breathe"
- Wide retrace (3% default) from high-water mark
- Patient: requires 3 consecutive breach checks before close
- Absolute price floor caps max loss
- Goal: don't get shaken out before the trade develops
Phase 2: "Lock the Bag"
- Tight retrace (1.5% default, per-tier overrides)
- Quick exit: 1-2 breaches to close
- ROE-based tier ratcheting — profit floors never go backward
- Per-tier retrace tightens as profit grows
ROE-Based Tiers
All triggers use ROE (Return on Equity): PnL / margin * 100. At 10x leverage, 1% price move = 10% ROE.
Usage
Standalone — Guard an existing position
hl guard start ETH-PERP \
--entry 2500.0 \
--size 1.0 \
--direction long \
--leverage 10 \
--preset tight \
--tick 5
Composable — Attach to any strategy
# config.yaml
strategy: avellaneda_mm
instrument: ETH-PERP
tick_interval: 10.0
guard:
enabled: true
preset: tight
leverage: 10.0
hl run avellaneda_mm --config config.yaml
Presets
| Preset | Tiers | Stagnation TP | Use Case |
|---|---|---|---|
moderate |
6 (10/20/30/50/75/100% ROE) | No | Standard trades |
tight |
4 (10/20/40/75% ROE) | Yes (8% ROE, 1hr) | Aggressive protection |
Module API
from modules.trailing_stop import TrailingStopEngine, GuardAction
from modules.guard_config import GuardConfig, PRESETS
from modules.guard_state import GuardState
config = PRESETS["tight"]
config.leverage = 10.0
config.direction = "long"
engine = TrailingStopEngine(config)
state = GuardState.new("ETH-PERP", entry_price=2500.0, position_size=1.0, direction="long")
result = engine.evaluate(price=2520.0, state=state)
# result.action: GuardAction.HOLD | .CLOSE | .TIER_CHANGED
# result.state: updated state (persist this)
# result.roe_pct, result.effective_floor, result.reason
What ships with it
1 file 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.
- 2d ago First seen · 192 lines · 95 tokens per session scan A 510fbf088625
guard-trailing-stop is a skill published in the GitHub repository Nunchi-trade/agent-cli (515 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 2,063 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…