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/upgradegit 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/upgrade)<a href="https://agentmods.dev/commands/madarauchiha-314/the-loop/upgrade"><img src="https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/upgrade.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 | $0.00632 |
| Opus 5 | $0.00000 | $0.00316 |
| Sonnet 5 | $0.00000 | $0.00126 |
| Haiku 4.5 | $0.00000 | $0.00063 |
Grade A, and why
upgrade 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 6d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
upgrade
Move an installed the-loop forward: the CLI and the Claude Code plugin.
the-loop upgrade [COMPONENT ...] [--scope user|project] [--project-dir .]
[--from owner/repo] [--dry-run] [--format table|json]
$ the-loop upgrade
the-loop upgrade · components: cli, claude · scope: user · marketplace: MadaraUchiha-314/the-loop
Component Outcome Step Command / file
--------- ------- -------------------------------- ------------------------------------------------
cli applied upgrade the the-loopy-one CLI /usr/bin/uv tool upgrade the-loopy-one
claude applied refresh the the-loop marketplace claude plugin marketplace update the-loop
claude applied update the-loop@the-loop claude plugin update the-loop@the-loop --scope user
Same command as install — same components, flags, outcomes,
scopes and exit codes — with the upgrade path of each installer instead of its install
path. Read that page for the mechanics; this one covers only what differs.
What differs
- The CLI is upgraded with the installer that owns it.
uv tool upgrade,pipx upgrade, orpip install --upgrade, chosen by where the running package actually lives. That is the point of the command: issue-78 was a CLI that kept reporting an old version because nobody remembered which installer had put it there. - The marketplace is refreshed first.
plugin marketplace update the-loopruns beforeplugin update the-loop@the-loop, so the update resolves against the current manifest rather than a cached one. - A source checkout is skipped, naming the checkout: a development install is updated
with
git pull(anduv sync), not by installing a release over it.
Claude Code applies a plugin update on the next session — restart the harness after an upgrade.
After upgrading the plugin
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.
- 6d ago First seen · 56 lines · 0 tokens per session scan A def7eb1c19b5
upgrade is a command published in the GitHub repository MadaraUchiha-314/the-loop (4 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 632 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.
duck-off
Turn off Rubber Duck mode and answer normally.
review-code
Agent review pass plus manual checklist for correctness, security, performance, and accessibility.
rls-plan
Supabase RLS + access-control audit + remediation plan — no SQL until approved.