mesh AGENTS.md

Project instructions for Mesh, a single-process Bun and Hono application with an embedded SQLite database. They document prerequisites, development commands, tests, environment settings, and the health check.

In plain words
What is it for?
Use them when installing dependencies, starting Mesh locally, running tests, checking the server, or working with its optional command-line tool.
Why use it?
They give a coding agent the project-specific details needed to run and test the application correctly without guessing which services are required.

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

Made for: Codex, OpenCode.

Per session 578 This file is loaded in full into every session.
When invoked 578 The same file — it is already loaded in full.
Security scan C 2 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 $0.00578 $0.00578
Opus 5 $0.00289 $0.00289
Sonnet 5 $0.00116 $0.00116
Haiku 4.5 $0.00058 $0.00058

Measured 3d ago against content hash 290f9be30bc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

mesh AGENTS.md scanned grade C with 2 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 3d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

`curl -fsSL https://bun.sh/install | bash -s bun-v1.3.11`

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`curl -fsSL https://bun.sh/install | bash -s bun-v1.3.11`
AGENTS.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Cursor Cloud specific instructions

Mesh is a single-process Bun + Hono app with embedded SQLite. There is no separate database, frontend dev server, or worker process.

Prerequisites

  • Bun 1.3.11 (matches Dockerfile). If bun is missing, install with: curl -fsSL https://bun.sh/install | bash -s bun-v1.3.11
  • Ensure $HOME/.bun/bin (or /usr/local/bin/bun) is on PATH.

Commands

Task Command
Install deps bun install
Dev server bun run devhttp://localhost:3000
Run (no hot reload) bun run start
Tests bun test src/*.test.ts
Lint (none configured)

Services

Only one service must run for end-to-end development: the Mesh server (bun run dev). SQLite is created automatically as mesh.db in the repo root (or under MESH_DATA_DIR when set).

Optional: cd cli && bun run dev for the mesh-rooms CLI — not required for dashboard/API work.

Environment variables

Copy .env.example to .env if needed. Defaults work for local dev on port 3000. See .env.example for ADMIN_ROOM_PASSWORD, DEFAULT_ROOMS, etc.

Hello-world check

curl http://localhost:3000/health
curl -X POST "http://localhost:3000/api/send?room=test&name=AgentA" \
  -H "Content-Type: application/json" -d '{"message":"hello"}'
curl "http://localhost:3000/api/messages?room=test&name=AgentB"

Open http://localhost:3000/dashboard?room=test for the web UI.

Dashboard tapbacks (+1 / yes / love)

  • Reactions use POST /api/react with the viewer name from the composer field (not the default you).
  • Claimed agent names require the token stored at localStorage['mesh-token:ROOM:NAME'] (set via /api/enter / invite flow). The dashboard sends it as x-agent-token.
  • Failed reactions must not flip the SSE connection badge; use apiAction() in dashboard.html, not api().

Gotchas

  • Do not run railway up or deploy — only Lisan al-Gaib deploys to Railway per CLAUDE.md.
  • No compile/build step; Bun runs TypeScript directly.
  • Playwright is in devDependencies but no npm script uses it yet.

Read the full file on GitHub · 55 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. 3d ago First seen · 55 lines · 578 tokens per session scan C 290f9be30bc9

Subscribe to this mod's changes

mesh AGENTS.md is an instructions file published in the GitHub repository ycanerden/mesh (5 stars, last pushed 17d ago), licensed MIT. It adds 578 tokens to every session, about $0.0029 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.