start

A project time-tracking command that starts a clock and can record the task, agent count, tags, notes, and billing status.

In plain words
What is it for?
Use it to begin tracking a task, record how many agents are involved, start a clock retroactively, and receive an entry ID for stopping or correcting it.
Why use it?
It prevents work time from being forgotten or priced incorrectly when several agents are working at once.

Command

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 commands/moshcoder/moshcode/start
Clone the repo
git clone --depth 1 https://github.com/moshcoder/moshcode
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 329 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00015 $0.00329
Opus 5 $0.00008 $0.00164
Sonnet 5 $0.00003 $0.00066
Haiku 4.5 $0.00002 $0.00033

Measured yesterday against content hash ed6127a90ded, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start 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.

plugins/timer/commands/start.md · 34 lines

What it actually says

Task

Start a clock for $ARGUMENTS.

timer start $ARGUMENTS --json

The first word is the project; everything after it is the task, so no quoting is needed. Useful flags:

  • --agents N — how many engines are working. An agent-priced rate multiplies by this, so it is the difference between a $400 afternoon and a $1,600 one.
  • --at 09:15 or --at -20m — the clock you meant to start earlier.
  • --tag, --note, --no-billable.

Rules

  • Do not pass --switch unless the user asked to stop their other clocks. Several clocks running at once is normal here: parallel agents each track their own work, and stopping someone else's is not recoverable from the log.
  • If started.alsoRunning comes back non-empty, mention how many other clocks are running. Do not stop them.
  • Report the entry id — timer stop --id <id> needs it, and so does the user if they want to correct the entry later.
  • If the command exits 2, the command line was wrong; read the error and fix it rather than retrying the same thing.
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. yesterday First seen · 34 lines · 15 tokens per session scan A ed6127a90ded

Subscribe to this mod's changes

start is a command published in the GitHub repository moshcoder/moshcode (2 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 329 once invoked, about $0.0001 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.