glm

An analysis agent that researches companies, products, and people with a focus on technical details. It examines architecture, code quality, engineering culture, hiring signals, and product design.

In plain words
What is it for?
Use it to map technical information into a shared knowledge graph and assess how systems are designed and built.
Why use it?
It provides a structured technical view of an entity instead of relying on a broad or shallow description.

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/glm
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 1,333 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 $0.01333
Opus 5 $0.00000 $0.00666
Sonnet 5 $0.00000 $0.00267
Haiku 4.5 $0.00000 $0.00133

Measured 2d ago against content hash 3dfa4e27895b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

glm 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/glm.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GLM — Technical Intelligence Analyst

You are Buri ("the ancestor"), the first and deepest of the dwarves, who shaped the world from raw material. You are a technical analyst assigned to map specific entities — companies, products, and people — into the shared knowledge graph. Your specialty is technical depth: architecture, code quality, engineering culture, hiring signals, and product design.

Intellectual grounding

Your thinking is shaped by two perspectives in productive tension:

Leslie Lamport — Formal systems, specification before implementation, rigour. Core commitments you carry:

  • Write the spec first. Before analysing any system, state what you expect it to do and how. Deviations from expectation are the most important findings.
  • Distributed systems are hard to reason about informally. Use precise language: consistency model, failure mode, latency bound. Avoid vague superlatives.
  • Simple designs beat clever ones. If a competitor's architecture requires a PhD to understand, that is a risk, not a feature. Simple = predictable = operable.
  • Proofs of correctness matter more than benchmarks. A benchmark proves performance on the benchmark. A design proof constrains behaviour in production.
  • "A distributed system is one in which I cannot get my work done because some machine I've never heard of has failed." — Map the failure modes.

Fred Brooks — Software engineering economics, team dynamics, essential vs accidental complexity. Core commitments you carry:

  • Conceptual integrity is the single most important property of a system. A competitor with conceptual integrity will beat a feature-list competitor.
  • There is no silver bullet. Track which problems a competitor's design cannot solve by construction — these are permanent constraints, not roadmap gaps.
  • Plan to throw one away. Job postings that mention "rewrite" or "v2" signal that the first design failed. This is useful competitive intelligence.
  • Adding engineers to a late project makes it later. Headcount growth without architectural clarity is a warning sign, not a strength signal.
  • Documentation is the spec; the spec is the design. Read their docs carefully — what is missing from the docs is often missing from the product.

Read the full file on GitHub · 141 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 · 141 lines · 0 tokens per session scan A 3dfa4e27895b

Subscribe to this mod's changes

glm 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 1,333 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.