evolith_arch32 AGENTS.md

A project instruction file for the beyondnetcode/evolith_arch32 repository. It documents the architecture, how to build and run the project, and which validation, pre-commit, and pre-push checks to use.

In plain words
What is it for?
Use it when working in this repository to review its reference documentation, run validation scripts, check bilingual documentation coverage, and follow its Git hooks.
Why use it?
It gives coding agents repository-specific rules and commands, reducing the chance that they use the wrong workflow or skip required checks.

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/beyondnetcode/evolith_arch32/agents-md
Clone the repo
git clone --depth 1 https://github.com/beyondnetcode/evolith_arch32

Made for: Codex, OpenCode.

Per session 2,225 This file is loaded in full into every session.
When invoked 2,225 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 $0.02225 $0.02225
Opus 5 $0.01112 $0.01112
Sonnet 5 $0.00445 $0.00445
Haiku 4.5 $0.00222 $0.00222

Measured yesterday against content hash 4991f01ded4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evolith_arch32 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 yesterday.

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 · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project

Open technical reference for products that start simple, mature into modular monoliths, and evolve into distributed services only when justified by product and operations.

This repository defines the architectural baseline, governance standards, harness rules, and reference implementation patterns used by satellite repositories. UMS is the official external executable product reference.

Build & Run

  • Reference docs review: use the root README.md, MASTER_INDEX.md, and reference/ tree first.
  • Applied product reference: https://github.com/beyondnetcode/ums
  • UMS setup and run commands: follow the current UMS README.md; this repository does not duplicate them.

Validation Scripts

Script Purpose
node .harness/scripts/ci/01-validate-docs.mjs Full documentation validation (links, anchors, encoding, Mermaid)
node .harness/scripts/ci/suites/bilingual-suite.mjs Verify EN/ES document coverage, reciprocity, and structural parity
node .harness/scripts/bilingual-coverage.mjs Report bilingual coverage (which files lack counterparts)
node .harness/scripts/coverage-dashboard.mjs Generate visual HTML/MD coverage report by area
node .harness/scripts/generate-executive-summary.mjs Generate the bilingual executive governance summary from the canonical gap and maturity evidence
node .harness/scripts/generate-executive-summary.mjs --check Verify the executive governance summary is current
node .harness/scripts/generate-es-skeleton.mjs <file.md> Create ES skeleton from EN file (with --dry-run flag)
python ./.bmad-core/scripts/cleanup_markdown_encoding.py Sanitize UTF-8 encoding issues
node .harness/scripts/ci/01-validate-docs.mjs --render-mermaid Render Mermaid diagrams to SVG for visual validation
node .harness/scripts/run-evolith-audit.mjs Print the Winston architectural audit prompt for LLM context
node .harness/scripts/run-evolith-audit.mjs --bmad Print the BMAD Agent Evolution prompt
node .harness/scripts/run-evolith-topology.mjs Run topology compliance audit (structural parity across all topologies)
node .harness/scripts/run-evolith-deep.mjs Run SDLC Deep Audit — 8-dimensional executable SDLC evaluation (JSON)
node .harness/scripts/run-evolith-deep.mjs --markdown SDLC Deep Audit with human-readable Markdown report
node .harness/scripts/run-evolith-intelligent-data-audit.mjs Winston intelligent data strength audit — evaluates WS1-WS9 workstream coverage
node .harness/scripts/run-evolith-intelligent-data-audit.mjs --es Intelligent data strength audit in Spanish
node .harness/scripts/run-evolith-intelligent-data-audit.mjs --ws1 Check only specific workstream (WS1-WS9)
node .harness/scripts/run-evolith-intelligent-data-audit.mjs --report Output JSON report only

Read the full file on GitHub · 133 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. yesterday First seen · 133 lines · 2,225 tokens per session scan A 4991f01ded4e

Subscribe to this mod's changes

evolith_arch32 AGENTS.md is an instructions file published in the GitHub repository beyondnetcode/evolith_arch32 (0 stars, last pushed 5d ago), licensed MIT. It adds 2,225 tokens to every session, about $0.0111 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.