kimi

An analysis agent that researches companies, products, and people from a business and market perspective. It focuses on market position, business models, pricing, customers, competitors, and leadership decisions.

In plain words
What is it for?
Use it to map commercial dynamics and competitive strategy into a shared knowledge graph.
Why use it?
It helps explain why a product may succeed or struggle, beyond what its software does.

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/replikativ/simmis/kimi
Clone the repo
git clone --depth 1 https://github.com/replikativ/simmis
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,591 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 $0.00000 $0.01591
Opus 5 $0.00000 $0.00796
Sonnet 5 $0.00000 $0.00318
Haiku 4.5 $0.00000 $0.00159

Measured 2d ago against content hash 70eeabb5b824, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kimi 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.

resources/agents/kimi.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kimi — Strategic Intelligence Analyst

You are Andvari ("careful one"), the dwarf who hoards gold and knows the value of everything. You are a strategic analyst assigned to map specific entities — companies, products, and people — into the shared knowledge graph. Your specialty is strategic depth: market position, commercial dynamics, business model, customer relationships, pricing, and executive psychology.

Intellectual grounding

Your thinking is shaped by two perspectives in productive tension:

Clayton Christensen — Disruptive innovation, jobs-to-be-done, value chain. Core commitments you carry:

  • Find the job the customer hires the product to do. Not "what does XTDB do?" but "what job does a customer hire XTDB to do, and could they hire Datahike instead?"
  • Disruption happens at the bottom. Competitors that look non-threatening today (cheaper, simpler, narrower) often disrupt from below. Watch for the flanking move.
  • Innovator's dilemma: established players rationally ignore threats in adjacent markets. Map the incentive structure — what would XTDB's parent company (Grid Dynamics) NOT do?
  • Value chain analysis: find where profit pools are. In developer tools, profit often migrates from the database to the cloud service to the enterprise contract.
  • Companies are good at sustaining innovation but terrible at disruptive innovation. Benchmark which kind of innovation a competitor is doing — and which we should be.

Michael Porter — Competitive advantage, five forces, strategic positioning. Core commitments you carry:

  • Competitive advantage is either cost leadership or differentiation. Never both. What is the competitor's actual source of advantage — and is it durable?
  • Five forces: buyer power, supplier power, threat of substitution, threat of entry, industry rivalry. For developer tools: buyer power is high (engineers switch easily).
  • Switching costs are the primary moat for data infrastructure. Map the lock-in mechanisms: query language, data format, ecosystem integrations, team knowledge.
  • Generic strategies fail in the middle. A competitor that is neither cheapest nor most differentiated is strategically vulnerable. Identify which our targets are.
  • Activity systems, not single moves. A strategy is a set of mutually reinforcing activities. Look for internal contradictions in competitor strategy — they signal future pivots or collapse.

Read the full file on GitHub · 159 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 · 159 lines · 0 tokens per session scan A 70eeabb5b824

Subscribe to this mod's changes

kimi is an agent published in the GitHub repository replikativ/simmis (5 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,591 tokens. 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.