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.
git clone --depth 1 https://github.com/alrece/loop-engineeringWrote 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/alrece/loop-engineering/adversarial)<a href="https://agentmods.dev/commands/alrece/loop-engineering/adversarial"><img src="https://agentmods.dev/badge/commands/alrece/loop-engineering/adversarial/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/alrece/loop-engineering/adversarial"><img src="https://agentmods.dev/badge/commands/alrece/loop-engineering/adversarial.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00063 | $0.01240 |
| Opus 5.5 | $0.00025 | $0.00496 |
| Sonnet 5.5 | $0.00013 | $0.00248 |
| Haiku 4.5 | $0.00006 | $0.00124 |
Grade A, and why
LOOP: Adversarial 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 1mo 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 1mo ago First seen · 58 lines · 63 tokens per session scan A cfb4c878f6c3
LOOP: Adversarial is a command published in the GitHub repository alrece/loop-engineering (2 stars, last pushed 3mo ago), with no licence file. It adds 63 tokens to every session and 1,240 once invoked, about $0.0003 per session on Opus 5.5. 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
improve
Apply systematic improvements to code quality, performance, and maintainability.
impl-review
John Carmack-level implementation review via Codex, Copilot, Cursor, Claude or a host reviewer.
resolve-pr
Resolve PR review feedback — fetch unresolved threads, triage, dispatch resolver agents, reply + resolve via GraphQL.
review-team
Parallel code review with 3 specialist lenses plus the kit-default kit:advisor extra lens. Dispatches the security, architecture, and test-coverage lenses simultaneously, adds the cross-cutting kit:advisor (critique mode), then merges findings.
OPSX: Continue
Continue working on a change - create the next artifact (Experimental).
devs-team
Parallel multi-lens critique of a solution design (the active spec if present, else the decision brief). Dispatches 5 engineering lenses, merges findings, reports a verdict. Report-only, never blocks.