AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Orca Strategy

skill-senpi-ai-senpi-skills-orca · by Senpi-ai

>-

↗ Repository
— No reviews yet
0 installs
11 views
0.0% view→install

Install

$ agentstack add skill-senpi-ai-senpi-skills-orca

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Orca Strategy? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

🐋 ORCA v4.0.0 — Gen-1 Vanilla Striker

v4.0.0 (2026-05-12) — plumbing-only migration

NO thesis change. v3.0 Gen-1 vanilla Striker logic preserved verbatim. Migration: mcporter → SenpiClient, scanner-side createposition → producer pushsignal() with LLM-gated runtime action, Python state files for daily cap → runtime.yaml risk.guard_rails, MARKET exits → FEEOPTIMIZEDLIMIT.

Back to pure FIRST_JUMP explosions.

v3.0 changelog (fleet-fix batch 4)

Reverted Gen-2 quality confirmation. Orca's own self-diagnosis: "Gen-2 confirmation adds latency and buys local tops after the move."

  • Removed leaderboard_get_momentum_events API call
  • Removed TCS ELITE/RELIABLE gate and ELITE_BONUS booster
  • Removed contribution_pct_change_4h acceleration booster
  • Back to single API call per scan (leaderboard_get_markets)
  • Leverage clamping applied to emitted entry (get_safe_leverage)

⛔ CRITICAL AGENT RULES

RULE 1: Install path is /data/workspace/skills/orca-strategy/

RULE 2: THE SCANNER DOES NOT EXIT POSITIONS — DSL only.

RULE 3: MAX 3 POSITIONS

RULE 4: Verify runtime on every session start

RULE 5: Never modify parameters

RULE 6: MAX 6 ENTRIES PER DAY

RULE 7: 120-minute per-asset cooldown

Runtime Setup

sed -i 's/${WALLET_ADDRESS}//' /data/workspace/skills/orca-strategy/runtime.yaml
sed -i 's/${TELEGRAM_CHAT_ID}//' /data/workspace/skills/orca-strategy/runtime.yaml
openclaw senpi runtime create --path /data/workspace/skills/orca-strategy/runtime.yaml
openclaw senpi runtime list
openclaw senpi status

Bootstrap Gate

On EVERY session start, check config/bootstrap-complete.json. If missing:

  1. Read senpi-trading-runtime skill
  2. Verify Senpi MCP
  3. Set wallet and telegram in runtime.yaml
  4. Install runtime
  5. Verify: openclaw senpi runtime list and openclaw senpi status
  6. Create scanner cron (90s, main)
  7. Write config/bootstrap-complete.json
  8. Send: "🐋 ORCA v3.0 online. Vanilla Striker. Silence = no explosions."

Risk

| Rule | Value | |---|---| | Max positions | 3 | | Max entries/day | 6 | | Leverage | 7x | | Cooldown | 120 min per asset | | Min score | 9 |

Files

| File | Purpose | |---|---| | scripts/orca-scanner.py | Gen-1 vanilla Striker scanner | | scripts/orca_config.py | Config helper | | config/orca-config.json | Wallet, strategy ID | | runtime.yaml | Runtime YAML for DSL plugin |

License

MIT — Built by Senpi (https://senpi.ai).

Skill Attribution

When creating a strategy, include skill_name and skill_version in the call. See references/skill-attribution.md for details.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills