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/startgit 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/start)<a href="https://agentmods.dev/commands/madarauchiha-314/the-loop/start"><img src="https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/start.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 | $0.00000 | $0.01202 |
| Opus 5 | $0.00000 | $0.00601 |
| Sonnet 5 | $0.00000 | $0.00240 |
| Haiku 4.5 | $0.00000 | $0.00120 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
start
Bring the-loop up: one command that reads the CLI config and starts, detached, every service it enables (issue-228, decision-084).
the-loop start
| Service | Enabled by | Default |
|---|---|---|
| Control-plane service (REST + dashboard) | service.enabled |
on |
MCP endpoint (/mcp, mounted on the service) |
service.mcp.enabled |
on |
| GitHub webhook receiver | webhooks.ghWebhook.enabled |
off |
| Poller | polling.enabled |
off |
| Standing sessions | standingSessions.enabled |
off |
The ingresses are explicit opt-ins: a config that merely describes a receiver or a
polling source must not open a port or start a loop. start prints one line per
service — started, hosted (see below), already-running (start is idempotent),
disabled (naming the key that enables it), misconfigured (an enabled poller with no
polling.sources), or failed (pointing at the service's logfile) — and exits 0 only
when every enabled service came up. One service failing never hides the others'
outcomes.
One process by default
With the service enabled and
service.hostIngresses at its default
(true, issue-231), start
boots one process: the service, which runs the enabled ingresses as background
threads inside its own lifespan. Each hosted ingress still holds its own pidfile lock —
under the service's pid — so status, stop and the daemons API answer unchanged, and
an ingress already running standalone is skipped with a warning, never fought over.
$ the-loop start
service started [enabled] started at http://127.0.0.1:4114; /mcp exposed
gh-webhook hosted [enabled] in the service process (pid 24846)
poller hosted [enabled] in the service process (pid 24846)
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.
- 4d ago First seen · 99 lines · 0 tokens per session scan A f59ce658199d
start 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 1,202 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
brainstorm
已弃用 - 请改用 superpowers:brainstorming 技能.
execute-plan
已弃用 - 请改用 superpowers:executing-plans 技能.
gaai-audit
Show workspace audit log with filters and optional JSON export.
gaai-ask
Search workspace memory — ranked entries with 1-hop graph context (cognitive guarantee).
gaai-update
Update the GAAI framework or switch AI tool adapter.
gaai-bootstrap
Initialize or refresh project context via Bootstrap Agent.