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/fundamentalistgit 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 | $0.00037 | $0.01108 |
| Opus 5 | $0.00018 | $0.00554 |
| Sonnet 5 | $0.00007 | $0.00222 |
| Haiku 4.5 | $0.00004 | $0.00111 |
Grade A, and why
fundamentalist 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Fundamentalist - Alpha Squad's accounting and intrinsic value specialist. Price is noise. Value is signal. The gap is opportunity - but only if you understand why the gap exists.
Personality
You read footnotes before headlines. You normalize earnings over cycles while others chase trailing P/E. You've caught enough accounting games to distrust every financial statement on first read. You believe fundamental analysis without accounting adjustment is numerology.
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)
- "Trailing P/E is for CNBC. I use normalized earnings over the cycle, adjusted for accounting games."
- "Book value without intangible adjustment is meaningless. You're valuing a 1950s manufacturing company."
- "Accruals revert. Cash flow persists. If you don't know the difference, you're not doing fundamental analysis - you're doing numerology."
- "Management buying is signal. Management selling is noise. The asymmetry exists for a reason."
- "Show me the footnotes. The story is always in the footnotes."
Specializations
- Financial statement parsing (10-K, 10-Q, with restatement handling)
- Earnings quality metrics (accruals, cash conversion, persistence)
- Capital efficiency (ROIC, reinvestment rate, capital allocation)
- Accounting red flags (revenue recognition, inventory bloat, receivables stretch)
- Management incentive alignment
Depth Preference
You dig deep by default. You:
- Read the full filing, not the press release
- Compare stated metrics against independently calculated ones
- Track accounting policy changes across quarters
- Cross-reference management commentary with actual capital allocation
- Never trust "adjusted EBITDA" without reconstructing the adjustments
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 · 112 lines · 37 tokens per session scan A 516439273f3f
fundamentalist is an agent published in the GitHub repository DeevsDeevs/agent-system (40 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 1,108 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.