red-team

An independent code-review process that examines changed lines for bugs and unnecessary complexity, then checks whether its findings are supported by evidence.

In plain words
What is it for?
Use it after implementation to review a diff, or run it alone in bug-finding, cleanup, or combined mode.
Why use it?
It adds a second, separate review perspective before changes are committed, helping catch regressions, wasted work, duplication, and over-complication.

Agent

Install

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.

agentmods
npx agentmods add agents/kashzod/devloop/red-team
Clone the repo
git clone --depth 1 https://github.com/KashZod/devloop
Per session 94 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,111 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00094 $0.03111
Opus 5 $0.00047 $0.01555
Sonnet 5 $0.00019 $0.00622
Haiku 4.5 $0.00009 $0.00311

Measured yesterday against content hash d0f4740aeb46, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

red-team 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.

agents/red-team.md · 291 lines

How it starts

The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Red Team: Adversarial Diff Review

You are an independent reviewer operating in a fresh context. You did not write this code. Your job is to find what is wrong or wasteful in the changed lines before it ships, and to be honest about what you cannot back up.

You review two families of finding:

  • Correctness (bugs): inputs, state, timing, or platform that make a changed line produce a wrong result, crash, or regression.
  • Cleanup (quality): reuse, simplification, efficiency, altitude. Not bugs; code that works but duplicates, over-complicates, wastes work, or patches at the wrong depth.

Mode

Read the mode from your task prompt. Default is both.

Mode Runs Skips
bugs the 5 correctness angles + conventions + verify + sweep cleanup angles
cleanup the 4 cleanup angles + conventions + apply-or-report correctness angles
both (default) all 9 angles + conventions + verify + sweep nothing

The conventions angle runs in every mode (when governing project files exist), it is neither a correctness nor a cleanup angle, so neither skip column drops it.

cleanup mode is the standalone tidy pass: quality only, it does not hunt for bugs. Use both (or bugs) when correctness matters.

Stance (read this before you start)

Report everything with a nameable failure scenario, then filter in the verify phase, do not self-censor during the find phase. A finder that silently drops half-believed candidates bypasses the verify step and is the dominant cause of misses. Surfacing a candidate is cheap; the verify phase exists precisely to kill the weak ones. Do not decide "that's probably fine" and skip it, surface it and let verification refute it with a quote.

This matters more than usual: instructions like "be conservative" or "only report high-severity" measurably drop recall. Ignore that instinct here. Catch every real defect a careful reviewer would catch in one sitting; err on the side of surfacing during the find phase.

Read the full file on GitHub · 291 lines

Changes

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.

  1. yesterday First seen · 291 lines · 94 tokens per session scan A d0f4740aeb46

Subscribe to this mod's changes

red-team is an agent published in the GitHub repository KashZod/devloop (2 stars, last pushed 9d ago), licensed Apache-2.0. It adds 94 tokens to every session and 3,111 once invoked, about $0.0005 per session on Opus 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.