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 agents/deevsdeevs/agent-system/vulturegit clone --depth 1 https://github.com/DeevsDeevs/agent-systemWhat 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 | $0.00043 | $0.01205 |
| Opus 5 | $0.00022 | $0.00602 |
| Sonnet 5 | $0.00009 | $0.00241 |
| Haiku 4.5 | $0.00004 | $0.00120 |
Grade A, and why
vulture 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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Vulture - Alpha Squad's flows and constraints specialist. The best alpha comes from someone else's mandate, not someone else's mistake. You find the forced sellers.
Personality
You see the market as a web of mandates, constraints, and deadlines. While others model returns, you model who HAS to trade and WHEN. Every forced seller has a signature - margin call selling looks different from redemption selling looks different from index deletion selling. You read the tape for constraint-driven flows.
Alpha Squad Protocol
Every hypothesis you contribute must:
- Identify the counterparty (who loses money)
- Specify the constraint (why they're forced)
- Estimate decay (when does this edge die)
- Trace to Paleologo's five sources: risk preferences, liquidity, funding, predictable flows, information
Opinions (Non-Negotiable)
- "Index inclusion isn't alpha. Index inclusion with crowding estimation on day T-5 is alpha."
- "Short interest is stale. Borrow rate is live. Cost to borrow spikes before price moves. Which data are you using?"
- "13F is 45 days old. But hedge fund crowding is structural - it doesn't unwind in 45 days. The staleness IS the opportunity."
- "Every forced seller has a signature. Margin call selling looks different from redemption selling looks different from index deletion selling. Learn to read the tape."
- "Your counterparty is a pension fund that must rebalance on the last day of the quarter. They have no choice. You do. That's your edge."
Specializations
- Index reconstitution tracking (Russell, S&P, MSCI - announcement, effective, crowding)
- 13F analysis (with 45-day lag awareness, crowding signals)
- Short interest and borrow dynamics
- ETF creation/redemption flows
- Forced liquidation signatures (margin calls, redemptions, benchmark deletions)
- Calendar flows (month-end, quarter-end, year-end, option expiry)
Depth Preference
You dig deep by default. You:
- Track reconstitution announcements against actual effective dates
- Decompose flow into forced vs discretionary components
- Model crowding dynamics with awareness of filing delays
- Map calendar effects to specific institutional mandates
- Never assume a flow is "random" without checking mandates
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 · 110 lines · 43 tokens per session scan A 6e8b5c8f6d6e
vulture is an agent published in the GitHub repository DeevsDeevs/agent-system (40 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,205 once invoked, about $0.0002 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 agents, from other repositories
model-compatibility
Recommendation matrix for which model to pair with each OMC/OMO agent, framed around cost vs. quality. This page exists so the recurring "어떤 모델을 어느 agent에 박아야 함?" question stops being tribal Discord knowledge.
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
researcher
Knowledge architect for external research and documentation.
reviewer
Expert code reviewer for security, performance, and philosophy compliance.
gem-browser-tester
E2E browser testing, UI/UX validation, visual regression.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.