standing

standing is a command for coding agents from MadaraUchiha-314/the-loop. It costs 0 tokens per session (2,234 once invoked), scanned A, original, MIT.

A named, ongoing terminal session managed by the-loop that is not tied to a ticket or work item.

In plain words
What is it for?
Use it to create, start, stop, restart, list, or send messages to persistent sessions, optionally assigning a working directory, harness, prompt, or Slack channel.
Why use it?
It provides a place for work that sits above individual tasks, without forcing that work into a ticket-based process with phases or completion rules.

Command

Part of the the-loop plugin — 2 skills, 37 commands, 2 hooks shipped together

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/madarauchiha-314/the-loop/standing
Clone the repo
git clone --depth 1 https://github.com/MadaraUchiha-314/the-loop

Or install the-loop, the plugin that ships this one along with the rest of its 2 skills, 37 commands, 2 hooks.

Wrote 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.

agentmods badge for standing

README.md
[![agentmods](https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/standing.svg)](https://agentmods.dev/commands/madarauchiha-314/the-loop/standing)
Your own site
<a href="https://agentmods.dev/commands/madarauchiha-314/the-loop/standing"><img src="https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/standing.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,234 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 $0.00000 $0.02234
Opus 5 $0.00000 $0.01117
Sonnet 5 $0.00000 $0.00447
Haiku 4.5 $0.00000 $0.00223

Measured 4d ago against content hash c710b08b2489, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

standing 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 4d 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.

docs/cli/commands/standing.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

standing

The sessions the-loop keeps for itself — declared in the CLI config, brought up by the-loop start, and addressed by name rather than by work item.

the-loop standing list [--format text|json]
the-loop standing create NAME [--harness H] [--cwd DIR] [--prompt TEXT|--prompt-file F]
                              [--description D] [--harness-arg ARG]... [--slack]
                              [--slack-channel C] [--no-auto-start] [--no-start]
the-loop standing delete NAME
the-loop standing start [NAME]      # omit NAME for every declared or created session
the-loop standing stop  [NAME]      # omit NAME for every recorded session
the-loop standing restart NAME
the-loop standing say NAME --text "…" [--actor WHO]

What a standing session is

Everything else the-loop spawns belongs to a ticket: the tmux session is named after the work item, events arrive from GitHub, and every question the agent asks goes back to the issue it came from. A standing session is the other kind — it owns no work item, so it has no ticket to be armed on, no phase to advance and no completion. It is what issue-277 asked for: somewhere for the work that sits above the work items, like watching the ones in flight and helping you recover one that is stuck.

Because there is no ticket, GitHub is not its surface. You talk to it here, over the control plane, or in a Slack thread of its own.

work-item session standing session
Addressed by github:OWNER/REPO#N a name
Started by an authorized the-loop start on the ticket the-loop start, or standing start
tmux session loop-<work-item-slug> loop-standing-<name>
Record <state.root>/local/<slug>.json <state.root>/local/standing/<name>.json
Defined by the ticket a config entry, or standing create
Answers arrive from ticket comments, routed by the daemon standing say, or its Slack thread
Ends when the work item is delivered you stop it

Read the full file on GitHub · 182 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. 4d ago First seen · 182 lines · 0 tokens per session scan A c710b08b2489

Subscribe to this mod's changes

standing is a command published in the GitHub repository MadaraUchiha-314/the-loop (4 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,234 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 2026-08-31.