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/lsendapp/lsend-cli/agents-mdgit clone --depth 1 https://github.com/lsendapp/lsend-cliWhat 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 | $0.01459 | $0.01459 |
| Opus 5 | $0.00730 | $0.00730 |
| Sonnet 5 | $0.00292 | $0.00292 |
| Haiku 4.5 | $0.00146 | $0.00146 |
Grade A, and why
lsend-cli 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.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
lsend CLI — Agent Integration Guide
Machine-readable, non-interactive CLI for the LocalSend protocol.
Progressive docs (offline): lsend agent [alias|scan|send|receive|errors|eval]
Cursor skill: skills/localsend-cli/SKILL.md (install to .cursor/skills/ or use npx skills add if published)
Principles
- No prompts — all inputs via flags
--json— structured stdout only (no human text); also enabled when stdout is piped orLSEND_NO_TUI=1--quiet— minimal stdout in human mode (--jsonimplies quiet)- Logs on stderr via
-v/RUST_LOG - Stable exit codes +
codefield in error JSON
Global flags
| Flag | Description |
|---|---|
--json |
JSON stdout (scan/send object, receive NDJSON); auto-enabled when piped |
--quiet / -q |
Suppress progress text (human mode) |
LSEND_NO_TUI=1 |
Same as --json for non-interactive stdout |
-v, --verbose |
Diagnostics on stderr |
--http |
Plain HTTP (default: HTTPS) |
--port PORT |
Default 53317. Keep 53317 for receive — alternate ports break multicast discovery (the LocalSend app and default scan will not see this device). |
--alias NAME |
Override persisted alias for one command only |
Exit codes
| Code | Meaning |
|---|---|
| 0 | Success |
| 1 | General error (code: "error") |
| 2 | Not found / validation (target_not_found, no_files, invalid_alias) |
| 3 | Port in use (port_in_use) |
scan
lsend scan --json --timeout 5000
{
"command": "scan",
"ok": true,
"timeout_ms": 5000,
"devices": [{ "alias": "...", "ip": "192.168.1.10", "port": 53317, "https": true, ... }]
}
Empty devices with ok: true is not an error.
alias
Manage the persisted device alias (the LocalSend app UI: Device name). Stored in ~/.config/lsend/alias.txt.
lsend alias show --json
lsend alias regenerate --json
lsend alias regenerate --json --locale zh-CN
lsend alias set "My Laptop" --json
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.
- yesterday First seen · 162 lines · 1,459 tokens per session scan A 2517f54438f6
lsend-cli AGENTS.md is an instructions file published in the GitHub repository lsendapp/lsend-cli (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,459 tokens to every session, about $0.0073 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.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.