mindwalk AGENTS.md

Architecture and design guidance for Mindwalk, a local visualizer that turns coding-agent session logs and repository structure into an explorable 3D code map.

In plain words
What is it for?
Working on the CLI, session trace export, repository city-map generation, browser playback, and optional session evaluation.
Why use it?
It keeps session parsing, repository mapping, playback, evaluation, and the web interface as separate parts with clear responsibilities.

Instructions file for CodexOpenCode

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 instructions/cosmtrek/mindwalk/agents-md
Clone the repo
git clone --depth 1 https://github.com/cosmtrek/mindwalk

Made for: Codex, OpenCode.

Per session 876 This file is loaded in full into every session.
When invoked 876 The same file — it is already loaded in full.
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 $0.00876 $0.00876
Opus 5 $0.00438 $0.00438
Sonnet 5 $0.00175 $0.00175
Haiku 4.5 $0.00088 $0.00088

Measured 2d ago against content hash fa435f02a4aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mindwalk AGENTS.md 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.

AGENTS.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

mindwalk is a local visualizer for coding-agent sessions. It supports Claude Code, Codex, and pi, turning agent session logs plus repository structure into a deterministic 3D "code city" that can be explored in a browser.

Design

The project has three primary artifacts:

  • A normalized trace of what happened during a supported coding-agent session.
  • A deterministic citymap of the repository being edited or inspected.
  • An evaluation report: an LLM judge's findings about one session — four fixed process dimensions plus a task-specific rubric layer — generated on explicit request only.

The UI combines those artifacts so users can see how a coding agent moved through a codebase over time — and, when asked, how well. Keep the separation clear: source-specific parsing should not know about rendering, citymap generation should not depend on session playback, the judge reads only the normalized trace (never raw session logs), and the server should mainly connect data sources to the web client.

Architecture

  • cmd/mindwalk provides the CLI commands: serve a local UI, open a session, build a citymap, export a trace, or evaluate a session.
  • internal/adapter converts supported agent session formats into the shared model. Claude Code, Codex, and pi each have an adapter; keep every source, current and future, behind its adapter boundary.
  • internal/model owns the trace, citymap, and report data contracts.
  • internal/citymap builds deterministic layouts from repository contents.
  • internal/judge renders a trace into an evidence document and runs a sealed local agent CLI (claude or codex) over it in up to two calls: the first drafts a task rubric — task-grouped criteria derived from the session's user messages — and the second is one unified scoring pass over the four fixed dimensions plus any rubric criteria. The rubric phase can skip (no events, no or too-little task text), reuse the cached report's rubric when the task wording is unchanged, or degrade to a dimensions-only report when generation fails; it never blocks the fixed layer. The judge subprocess gets no tools; verdicts — per dimension and per criterion — are always derived mechanically from finding severities and coverage, never decided by the LLM. Reports are cached in ~/.mindwalk/reports; docs/dynamic-rubric-evaluation.md explains the rubric layer.
  • internal/server exposes local APIs and serves the web app. internal/server/static holds the embedded frontend assets generated from web/dist.
  • web contains the React, Vite, and Three.js frontend.
  • schema mirrors the exported JSON contracts.

Read the full file on GitHub · 46 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 · 46 lines · 876 tokens per session scan A fa435f02a4aa

Subscribe to this mod's changes

mindwalk AGENTS.md is an instructions file published in the GitHub repository cosmtrek/mindwalk (1,305 stars, last pushed 23d ago), licensed MIT. It adds 876 tokens to every session, about $0.0044 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.