red-team

An adversarial code reviewer that examines how features interact across user interfaces, command-line tools, files, and separate processes.

In plain words
What is it for?
Use it as a final review after other reviewers, particularly for changes involving cancellation, background processes, shared files, or saved data.
Why use it?
It looks for bugs that specialist reviews may miss, such as race conditions, cleanup failures, outdated data formats, and differences between reported and actual results.

Agent for Claude Code

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/craftled/openklip/red-team
Clone the repo
git clone --depth 1 https://github.com/craftled/openklip

Made for: Claude Code.

Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 324 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 $0.00061 $0.00324
Opus 5 $0.00030 $0.00162
Sonnet 5 $0.00012 $0.00065
Haiku 4.5 $0.00006 $0.00032

Measured 2d ago against content hash 9080a24dbb60, 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 2d 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.

.claude/agents/red-team.md · 19 lines

What it actually says

You are the red team. Specialists have already swept the diff dimension by dimension; the brief lists what they found. Your only job is what they missed. Do not re-report their findings.

Think like an attacker and a chaos engineer, at the seams:

  • Interactions BETWEEN features and surfaces (GUI server actions vs CLI vs the spawned MCP process; two writers, one file).
  • Process boundaries: in-process locks that a second process bypasses, kill signals that miss children, registries that die with the server, env leakage between concurrent runs.
  • Lifecycle races: cancel vs natural completion, double-finalize, stale reads resurrecting terminal state, cleanup in finally blocks that never run on crash.
  • Schema evolution: older builds parsing newer files, unknown-key stripping, corrupt-file recovery paths that themselves throw.
  • The gap between what a UI claims (cancelled, completed, verified) and what the processes actually did.

Evidence gate: quote the motivating file:line plus verbatim code for every finding or force confidence to 4-5. End by listing what you checked and CLEARED, so the absence of findings is informative.

Output: one JSON object per line (same schema as reviewer, specialist:"red-team"); NO FINDINGS if nothing survives.

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. 2d ago First seen · 19 lines · 61 tokens per session scan A 9080a24dbb60

Subscribe to this mod's changes

red-team is an agent published in the GitHub repository craftled/openklip (2 stars, last pushed 23d ago), licensed MIT. It adds 61 tokens to every session and 324 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

demo-producer

Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.

yonatangross/orchestkit · 42 tokens

ui-surfaces

The AI summary card and its proposal choreography, the internals panel, the settings tabs, and the sidebar wake queue.

matthiasn/lotti · 24 tokens

AGENTS

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

patchy631/ai-engineering-hub · 0 tokens

dynamic-agents

Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.

VoltAgent/voltagent · 0 tokens

langgraph

LangGraph is a framework for developing applications powered by language models. Integrating LangGraph with the Model Context Protocol (MCP) allows agents to utilize tools defined across one or more MCP servers, enabling seamless interaction with external data sources and services.

IBM/mcp-context-forge · 0 tokens

verify-agent

구현 완료 후 fresh-context 검증 전용. typecheck → lint → build → test 파이프라인 독립 실행. 단순 에러(import·타입) 자동 수정, 비수정 가능 에러 분류 보고. Use proactively — 비단순 코드 변경 완료 직후 사람 호출("검증해줘"·"빌드 확인")을 기다리지 말고 자율 spawn한다. 완료 주장 전 필수(verification.md 자율 검증 §11). 사람 발화에 의존하지 않는다. /handoff-verify 스킬에서도 자동 스폰. 구현 자체는 tdd-guide나 impl-worker 사용.

sangrokjung/claude-forge · 134 tokens