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 instructions/siddsachar/row-bot/agents-mdgit clone --depth 1 https://github.com/siddsachar/row-botWhat 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 | $0.02596 | $0.02596 |
| Opus 5 | $0.01298 | $0.01298 |
| Sonnet 5 | $0.00519 | $0.00519 |
| Haiku 4.5 | $0.00260 | $0.00260 |
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.
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:
- Protect local user data, secrets, and local-first defaults.
- Avoid surprise network calls, provider calls, or real channel messages.
- Preserve approval gates and graceful recovery for destructive actions.
- Add deterministic tests for changed behavior.
- 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_providerore2e. - Do not add substantive tests to
tests/test_suite.py,tests/integration_tests.py, ortests/test_memory_e2e.py; they are retired compatibility shims. - Do not edit
requirements.txtby hand. It is generated fromuv.lock. - Do not add runtime implementation code to root wrappers such as
app.pyorlauncher.py; application code belongs undersrc/row_bot/. - Do not recursively delete ignored/generated directories such as
.tmp/,.testtmp/,dist/, orinstaller/build/unless explicitly asked. - Keep changes scoped. Avoid unrelated refactors, reformatting, and metadata churn.
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.
- 3d ago First seen · 251 lines · 2,596 tokens per session scan A 7e2752254def
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.
Other instructions, from other repositories
langchain-aws AGENTS.md
Instructions for langchain-ai/langchain-aws, covering global development guidelines for the langchain monorepo, project architecture and context, langchain-aws structure, key components and langgraph-checkpoint-aws structure.
MaxKB CLAUDE.md
Claude Code instructions for 1Panel-dev/MaxKB, covering claude.md, project overview, development commands, database / static and architecture.
docmind-ai-llm AGENTS.md
Instructions for BjornMelin/docmind-ai-llm, covering docmind ai: agent instructions, purpose, layout, quick commands with uv and non-negotiables for ci and security.
intentKeeper CLAUDE.md
Instructions for Olawoyin007/intentKeeper, covering claude.md, project overview, development commands, install with dev dependencies and start the classification server.
pxx AGENTS.md
Instructions for cdnwetzel/pxx, covering agents.md — working agreements for ai agents in this repo, what this is, commands, hard rules and conventions.
mcp-local-llm AGENTS.md
Instructions for aplaceforallmystuff/mcp-local-llm, covering agents.md - mcp-local-llm, tech stack, architecture, development commands and environment variables.