Lody is a shared workspace that connects coding agents running on different computers and lets people view and direct their work from desktop, mobile, web, or a command line. Teams use it to share agent conversations, monitor progress and code changes, and assign work to connected machines while retaining their existing agents and configurations.
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.
git clone --depth 1 https://github.com/LodyAI/LodyWrote 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/commands/lodyai/lody/agents)<a href="https://agentmods.dev/commands/lodyai/lody/agents"><img src="https://agentmods.dev/badge/commands/lodyai/lody/agents/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/lodyai/lody/agents"><img src="https://agentmods.dev/badge/commands/lodyai/lody/agents.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.01812 |
| Opus 5.5 | $0.00000 | $0.00725 |
| Sonnet 5.5 | $0.00000 | $0.00362 |
| Haiku 4.5 | $0.00000 | $0.00181 |
Grade A, and why
AGENTS 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 2d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
apps/cli/src/commands
CLAUDE.md is a symlink to this file. Edit AGENTS.md only.
Parent rules apply; see Session rules.
Process and daemon lifecycle
- One-shot commands use
runOneShotCommandfor consistent exits/flush. Await application disposal after fleet cleanup; cleanup failures exit nonzero. - Process entrypoints, command-owned boundaries, global process-error handlers, and generated
standalone shims may force exit after their own cleanup policy:
start.tsowns startup, fatal, and signal exits;daemon-runner.tsowns watchdog fatal and signal exits. Never force exit from reusable libraries, session/agent internals, TUI/watch flows, or worker code — expose cleanup and let the process boundary decide. - Remote restart/upgrade: attempt a bounded ACK; even on delivery failure, accepted
work asks
start.tsto exit with the lifecycle code for watchdog restart/upgrade. See ACK contract. - Upgrade handoff must use the verified entry from the installing npm's global root,
never the old watchdog's argv or a PATH-resolved
lody. Success requires the replacement's ready report to match the installed version; ordinary launches still accept legacy readiness. See upgrade contract. lody daemon startresolves cloud authentication in the FOREGROUND process before spawning the detached runner (daemon-auth-preflight.ts): validate the cached credential, and on a missing/rejected one run the interactive device-authorization flow there. An unreachable backend aborts instead of re-authenticating, and a non-TTY run aborts instead of blocking on a browser link.--skip-auth-checkis the opt-out;--authkeeps its non-interactive path.- The runner's fd 3 launch handshake reports success only after its supervised Worker reaches
startupStage=ready. An initial Worker exit returns bounded output and terminates the runner instead of claiming success; retryable startup exits keep the handshake pending, and a timeout terminates and awaits the exact spawned runner before reporting failure. - Cloud-mode
lody daemon statusreads the runtime probe's explicitbackendauthorization/connection state andconnectedWorkspaces; local mode omits that cloud-only block. Aggregateconnectivityis local runtime health and must not be presented as proof that the cached CLI token was accepted. - Connection-age fields preserve one continuous non-connected interval across
connecting/disconnected transitions and clear only on connected. Keep them in the top-level
connectionAgesv1 extension: older consumers reject unknown keys inside the strict backend/workspace objects. Status reports a red connection error at 60 seconds.
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.
- 2d ago Changed 346d77ac61ca
- 7d ago Changed 096aa23b6bd9
- 9d ago Changed · +5 lines 2d42f114d909
- 15d ago Changed · +3 lines f9d08b90d639
- 18d ago Changed · +6 lines 592c4e3ba2c3
- 23d ago Changed · -1 lines 856fa1a88d0b
- 1mo ago Changed · -5 lines 7a50a2b4701b
- 1mo ago Changed 6cc7cf164056
- 1mo ago Changed · +32 lines 105d424c0055
- 1mo ago First seen · 80 lines · 0 tokens per session scan A 49c5a66ee22d
AGENTS is a command published in the GitHub repository LodyAI/Lody (1,435 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,812 tokens. 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 commands, from other repositories
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
speckit.archive
Archive a feature specification into main project memory after merge, resolving gaps and conflicts.
speckit.opsmill.retrospect
Run a session retrospective that surfaces context-management gaps and routes them to approved follow-up actions.
pr
Handle the full workflow from current branch state to an open, CI-monitored pull request.
create-issue
Transform feature descriptions, bug reports, or improvement ideas into well-structured GitHub issues.
speckit.extract
Extract ADRs, knowledge, and guidelines from completed specifications into dev/ documentation.