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/criticgit 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/critic)<a href="https://agentmods.dev/commands/madarauchiha-314/the-loop/critic"><img src="https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/critic.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 | $0.01116 |
| Opus 5 | $0.00000 | $0.00558 |
| Sonnet 5 | $0.00000 | $0.00223 |
| Haiku 4.5 | $0.00000 | $0.00112 |
Grade C, and why
critic scanned grade C with 1 finding 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 5d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
`; rm -rf /` is a string the critic reads, not something the shell expands. How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
critic
The seam by which the harness doing the work hands it to a different harness for a critic round, and reads back what it said.
the-loop critic list [--root .] [--format table|json]
the-loop critic run <name> (--prompt TEXT | --prompt-file PATH)
[--root .] [--cwd DIR] [--work-item ID] [--spec-dir PATH]
[--timeout SECONDS] [--output-file PATH]
A review is worth more when it comes from a model that did not write the code. This command is how that happens without either harness knowing about the other.
Where critics come from
reviews.critics[] in the repository's
harness config. Each entry is
either:
- a
harnessthe-loop has an adapter for —claude,cursor— where the invocation is derived; or - an explicit
command(argv[0]) plusargs, with element-wise placeholders:{prompt},{promptFile},{model},{workItem},{specDir},{cwd}.
env overlays the inherited environment, and outputFormat, timeoutSeconds, cwd and
enabled complete the entry.
::: danger This is executable config in a committed file
A critic entry becomes an argv the CLI spawns. Review one the way you would review code, and
never put a secret in env — the file is committed.
:::
list
Every configured critic with its executable and whether that executable is available.
| Flag | Default | Meaning |
|---|---|---|
--root |
. |
Project root. |
--format |
table |
table or json. |
run
Run one named critic round.
| Flag | Default | Meaning |
|---|---|---|
| (positional) | — | The reviews.critics[] entry to run, by name. |
--prompt |
— | The review prompt, inline. |
--prompt-file |
— | File holding the prompt. Preferred — review prompts are long. |
--root |
. |
Project root. |
--cwd |
the critic's cwd, else --root |
Directory to run in. |
--work-item |
"" |
Work item id, e.g. issue-117 — fills {workItem}. |
--spec-dir |
<specDir>/<work item> |
Fills {specDir}. |
--timeout |
the critic's timeoutSeconds |
Override for this round. |
--output-file |
— | Also write the JSON envelope to this path. |
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.
- 5d ago First seen · 119 lines · 0 tokens per session scan C 68f09ddf6f5c
critic 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 1,116 tokens. A static security scan graded it C with 1 finding (recursive force delete). 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.