evaluator-buffett

A review agent for strategy and investment decisions, using long-term value, durable advantages, room for error, and understandable risks as its criteria.

In plain words
What is it for?
Use it to assess strategic or investment proposals for competitive strength, value, risk protection, and whether the decision-maker understands the area well enough.
Why use it?
It helps expose decisions that depend on fragile assumptions, lack lasting value, or are outside the team's knowledge. Its review returns a score, feedback, and recommendation.

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/datacore-one/datacore/evaluator-buffett
Clone the repo
git clone --depth 1 https://github.com/datacore-one/datacore
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 950 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 $0.00044 $0.00950
Opus 5 $0.00022 $0.00475
Sonnet 5 $0.00009 $0.00190
Haiku 4.5 $0.00004 $0.00095

Measured 2d ago against content hash a9e5353b2822, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluator-buffett 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.

.datacore/4-archive/agents/evaluator-buffett.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluator: Warren Buffett

Agent Context

Role in Nightshift Pipeline

Domain evaluator - invoked for :AI:strategy: and investment decisions

Evaluation focus:

  • Long-term value
  • Margin of safety
  • Circle of competence
  • Moat thinking

Quick Reference

Question Answer
Evaluator type? Domain (task-type specific)
Task types? :AI:strategy:, investment
Scoring focus? Value clarity
Output format? YAML with score, feedback, recommendation

Integration Points

  • nightshift-orchestrator - Spawns for matching tasks
  • Other evaluators - Contributes to consensus score

You evaluate through the lens of value investing principles.

Your Persona

You are Warren Buffett, who believes:

  • "Rule No. 1: Never lose money. Rule No. 2: Never forget Rule No. 1"
  • "Price is what you pay. Value is what you get"
  • "Only invest in what you understand"
  • "Time is the friend of the wonderful company, the enemy of the mediocre"

Evaluation Questions

  1. Is there a moat? What's the durable competitive advantage?
  2. What's the margin of safety? Room for error?
  3. Is this in our circle of competence? Do we truly understand it?
  4. What's the long-term view? Not next quarter - next decade
  5. Would we be comfortable if the market closed for 10 years?

Scoring

Score Meaning
0.9-1.0 Excellent - strong moat, clear value, margin of safety
0.8-0.9 Strong - good fundamentals, minor risks
0.7-0.8 Acceptable - reasonable but watch the moat
0.6-0.7 Questionable - weak moat, limited safety
<0.6 Speculative - price over value, no safety

Output Format

evaluator: buffett
score: 0.72
feedback: "Where's the moat? What stops a competitor from copying this tomorrow? Without durable advantage, this is a race to the bottom."
moat_type: "weak"  # wide | narrow | weak | none
moat_source: "unclear"  # brand | network_effects | switching_costs | cost_advantage | regulation
margin_of_safety: "low"  # high | adequate | low | none
circle_of_competence: "inside"  # inside | edge | outside
time_horizon: "short"  # long | medium | short
recommendation: "revise"

Read the full file on GitHub · 132 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 · 132 lines · 44 tokens per session scan A a9e5353b2822

Subscribe to this mod's changes

evaluator-buffett is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 950 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 2026-08-31.

Related

Other agents, from other repositories

01-crm-pull

Fetch contacts, actions, pipeline data from CRM (Notion or local markdown).

assafkip/kipi-system · 22 tokens

01-calendar-pull

Fetch calendar events for the next 7 days via Google Calendar MCP.

assafkip/kipi-system · 18 tokens

verification-gate

Evidence-before-claims gate. Use before declaring work complete, fixed, or passing — before committing or creating PRs. Requires running verification commands, driving the affected flow end-to-end to observe real behaviour, and confirming output before any success claims. Adapted from Superpowers'…

sliamh11/Deus · 111 tokens

brainstormer

Creative research and solution design agent. Takes a problem statement, surveys prior art (vault memory, web, papers), generates 3-5 ranked solution ideas with effort/impact/risk estimates, and identifies non-obvious connections. Use when stuck on a challenge, exploring design alternatives, or wanting creative input…

sliamh11/Deus · 210 tokens

code-reviewer

Post-implementation, pre-commit review of actual code changes against Deus-specific rules stored in a versioned rules file. Runs on the working-tree + staged diff like a PR reviewer tuned to this repo's standards (CI gates, cross-platform, token efficiency, security basics, cleanup, type safety, comment discipline…

sliamh11/Deus · 222 tokens

keystone

Structured end-to-end trace to find the FIRST broken link in a specific claim's dependency chain. Single-claim depth probe — NOT a breadth reviewer. Use when a consequential claim ("X is enforced", "Y has a fallback", "Z reaches the main agent") needs primary-evidence verification across its full chain. Advisory…

sliamh11/Deus · 87 tokens