row-bot AGENTS.md

Project instructions for AI coding agents working on Row-Bot, a local-first desktop AI assistant. They describe the project, its directory structure, working rules, and safeguards for data, network access, and destructive actions.

In plain words
What is it for?
Use them before changing Row-Bot code to understand the project map, follow its development rules, avoid unexpected network or message actions, and run the required tests.
Why use it?
They give an agent the context and constraints needed to edit the repository safely and consistently. They also require tests for changed behavior and protection of user data and approval steps.

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/siddsachar/row-bot/agents-md
Clone the repo
git clone --depth 1 https://github.com/siddsachar/row-bot

Made for: Codex, OpenCode.

Per session 2,596 This file is loaded in full into every session.
When invoked 2,596 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 $0.02596 $0.02596
Opus 5 $0.01298 $0.01298
Sonnet 5 $0.00519 $0.00519
Haiku 4.5 $0.00260 $0.00260

Measured 3d ago against content hash 7e2752254def, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

row-bot 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 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.

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 · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Canonical instructions for AI coding agents working in Row-Bot. Keep this file concise, concrete, and aligned with scripts/run_test_matrix.py.

Project Identity

Row-Bot is a local-first desktop AI assistant with provider-aware agent runtimes, tools, workflows, durable memory/knowledge graph data, MCP, plugins, skills, channels, voice, Developer Studio, Designer Studio, and platform installers.

Priorities, in order:

  1. Protect local user data, secrets, and local-first defaults.
  2. Avoid surprise network calls, provider calls, or real channel messages.
  3. Preserve approval gates and graceful recovery for destructive actions.
  4. Add deterministic tests for changed behavior.
  5. Keep Windows and macOS first-class; keep Linux browser/server mode healthy.

Ground Rules

  • Do not add Row-Bot first-party telemetry, analytics, or hidden phone-home behavior. A third-party dependency with telemetry may be used only when its behavior is reviewed, documented, disclosed before installation or first execution, and accepted by the user. Never describe third-party telemetry as Row-Bot telemetry, and never allow dependency telemetry to include Row-Bot prompts, files, memories, secrets, screenshots, tool arguments, or channel content. The reviewed, opt-in Cua Driver integration is the only currently approved exception; future dependencies require a separate review.
  • Do not commit secrets, API keys, provider tokens, private local paths, or real user data in code, tests, docs, fixtures, snapshots, or logs.
  • Do not make default tests depend on live providers, live MCP servers, real messaging channels, real network availability, or a specific local Ollama model. Mark those tests live_provider or e2e.
  • Do not add substantive tests to tests/test_suite.py, tests/integration_tests.py, or tests/test_memory_e2e.py; they are retired compatibility shims.
  • Do not edit requirements.txt by hand. It is generated from uv.lock.
  • Do not add runtime implementation code to root wrappers such as app.py or launcher.py; application code belongs under src/row_bot/.
  • Do not recursively delete ignored/generated directories such as .tmp/, .testtmp/, dist/, or installer/build/ unless explicitly asked.
  • Keep changes scoped. Avoid unrelated refactors, reformatting, and metadata churn.

Read the full file on GitHub · 251 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 · 251 lines · 2,596 tokens per session scan A 7e2752254def

Subscribe to this mod's changes

row-bot AGENTS.md is an instructions file published in the GitHub repository siddsachar/row-bot (1,479 stars, last pushed 5d ago), licensed Apache-2.0. It adds 2,596 tokens to every session, about $0.0130 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.