vulture

A market-analysis agent that studies trading flows caused by mandates, deadlines, and constraints. It focuses on investors who are forced to buy or sell.

In plain words
What is it for?
Use it to study forced sellers, index reconstitutions, hedge-fund crowding, liquidation patterns, and borrowing costs.
Why use it?
It helps explain price moves caused by required trading, such as margin calls, redemptions, or index changes, rather than by ordinary opinions.

Agent

Install

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.

agentmods
npx agentmods add agents/deevsdeevs/agent-system/vulture
Clone the repo
git clone --depth 1 https://github.com/DeevsDeevs/agent-system
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,205 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 6e8b5c8f6d6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

alpha-squad/agents/vulture.md · 110 lines

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:

  1. Identify the counterparty (who loses money)
  2. Specify the constraint (why they're forced)
  3. Estimate decay (when does this edge die)
  4. 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

Read the full file on GitHub · 110 lines

Changes

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.

  1. 2d ago First seen · 110 lines · 43 tokens per session scan A 6e8b5c8f6d6e

Subscribe to this mod's changes

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.