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 commands/madarauchiha-314/the-loop/indexgit clone --depth 1 https://github.com/MadaraUchiha-314/the-loopWrote 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/madarauchiha-314/the-loop/index)<a href="https://agentmods.dev/commands/madarauchiha-314/the-loop/index"><img src="https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/index.svg" alt="Measured on agentmods" 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 | $0.01310 |
| Opus 5 | $0.00000 | $0.00655 |
| Sonnet 5 | $0.00000 | $0.00262 |
| Haiku 4.5 | $0.00000 | $0.00131 |
Grade A, and why
index 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commands
the-loop --help
the-loop --version
the-loop --config path/to/cli-config.yaml <command> # must precede the subcommand
The control plane
Since issue-161 every command below that touches the-loop's state runs through the control-plane service, which is the single implementation of each capability. It is started for you on first use, so nothing here needs setting up first.
| Command | What it does |
|---|---|
start |
Bring up every service the CLI config enables — the control-plane service (+ /mcp), the webhook receiver, the poller. |
stop |
Stop every running the-loop service, whatever the enabled flags say now. |
status |
Per-service liveness and the poller's progress; exit 0 iff everything enabled is running. |
restart |
stop then start, optionally upgrading the CLI in between (--with-upgrade). Also POST /api/v1/restart. |
Daemon commands
Long-running or machine-scoped. Their own settings come from the CLI config and from nowhere else — no repository configures the daemon (decision-044). When they act on a work item they still read that item's own checkout, the same way the repo-scoped commands do.
| Command | What it does |
|---|---|
sessions |
The work-item ↔ session registry, execution control (start/pause/resume/stop), and reset — forget a work item's state so it starts over. |
standing |
The sessions the-loop keeps for itself — no work item, addressed by name: list, start, stop, restart, and say to talk to one. |
ask |
Post an agent's question on its work item — marker stamped centrally, wait recorded as session.awaiting_input. |
add-collaborator |
Give one GitHub login a voice on one work item: their comments become input for its session, and nothing else. |
remove-collaborator |
Take that voice back; it lapses on the next event. |
channels |
Operate the conversation channels (the Slack bot): status, one poll cycle, or the Socket Mode listener. |
events |
Query the structured event log — the answer to "why did nothing happen?". |
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 Changed · +2 lines ba270c4940b9
- 5d ago First seen · 89 lines · 0 tokens per session scan A df61d01605f0
index is a command published in the GitHub repository MadaraUchiha-314/the-loop (4 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,310 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.
Other commands, from other repositories
receipts
Find the receipt. A dated line, or it did not happen.
ship
Seen on their staging, then live. Rollback you have run.
negative-keyword-sweep
Find wasted spend in Google Ads search terms and add negatives at the right scope (account list, campaign, or ad group). Use when the user says "find junk keywords", "stop wasting on bad searches", or wants a search-terms cleanup.
import
Import a shared context bundle, or take a teammate's newer copy of one you already have.
duck-off
Turn off Rubber Duck mode and answer normally.
extensions
Show what the connected context expects to reach, and whether this machine provides it.