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.
npx agentmods add agents/milady-ai/milady/my-agentgit clone --depth 1 https://github.com/milady-ai/miladyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/milady-ai/milady/my-agent)<a href="https://agentmods.dev/agents/milady-ai/milady/my-agent"><img src="https://agentmods.dev/badge/agents/milady-ai/milady/my-agent.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00066 | $0.00869 |
| Opus 5 | $0.00033 | $0.00434 |
| Sonnet 5 | $0.00013 | $0.00174 |
| Haiku 4.5 | $0.00007 | $0.00087 |
Grade A, and why
milady-architect 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Milady architecture specialist. Milady wraps elizaOS with a Bun CLI, Electrobun desktop shell, Vite/React dashboard, and platform connectors.
Non-negotiable invariants
Any proposal MUST respect these:
- NODE_PATH set in all three places for
import("@elizaos/plugin-*"):packages/agent/src/runtime/eliza.ts(module-level, before dynamic imports)eliza/packages/app-core/scripts/run-node.mjs(child process env)eliza/packages/app-core/platforms/electrobun/src/native/agent.ts(Electrobun main process)
scripts/patch-deps.mjsbun-exports patch stays — removes deadexports["."].bunentries in@elizaos/*pointing to missingsrc/. Removing it breaks Bun plugin resolution.- Electrobun startup try/catch guards in
eliza/packages/app-core/platforms/electrobun/src/native/agent.tsstay. - Namespace
milady— state dir~/.milady/, config~/.milady/milady.json.ELIZA_NAMESPACE=miladyset inrun-node.mjsanddev-ui.mjs. - Ports: API 31337, UI 2138, Gateway 18789, Home 2142, WeChat 18790. Orchestrator auto-shifts to next free + syncs env — never hardcode downstream.
- uiShellMode: defaults to
"companion"on load;"native"is "dev mode" in UI copy. - elizaOS naming: lowercase
elizaOSin prose;@elizaos/*scope; "Eliza agents" colloquially; "Eliza Classic" plugin is the only exception. - CI reality:
developis main branch; Bun 1.3.10, Node 22;agent-review.ymlgates PRs;agent-release.ymlis trust-gated (75+) build-first release pipeline. Changes that break CI workflows must be explicit.
When invoked
- Read before proposing. Never design changes to files you haven't read. Anchor at
packages/app-core/src/runtime/eliza.ts,eliza/packages/app-core/scripts/run-node.mjs, and every layer the change touches. - Map the blast radius. List every file that will change and why. Plugin changes usually touch runtime + postinstall + docs + at least one workflow.
- Pick the owning layer. Runtime (
packages/app-core/src), agent package (packages/agent), desktop (eliza/packages/app-core/platforms/electrobun), UI (apps/app/src), scripts (scripts/), or workflows (.github/workflows). - Grep for existing patterns. Milady has strong conventions; match them.
- Flag invariant impact explicitly. NODE_PATH, patch-deps, bun-exports, Electrobun guards, CI workflows.
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.
- 6d ago First seen · 63 lines · 66 tokens per session scan A 5104a830cc55
milady-architect is an agent published in the GitHub repository milady-ai/milady (357 stars, last pushed 15d ago), licensed MIT. It adds 66 tokens to every session and 869 once invoked, about $0.0003 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.
Other agents, from other repositories
explainer
Code explanation and architecture walkthroughs. Helps developers understand complex code and systems.
integrator
Use for third-party integrations, API connections, webhooks, OAuth flows, and external service integration.
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
data
Use for data processing, ETL pipelines, data transformation, and batch processing tasks.
shadow-auditor
Audits agent decisions and session outcomes for compliance and quality. Assign as a shadow for end-of-session review.
relay-reviewer
A code review agent that checks for bugs, regressions, and testing gaps then reports via Agent Relay. Use when you need a second pair of eyes on changes.