cldcde: Skill for Claude Code

.claude/skills/red-team-tribunal/SKILL.md

red-team-tribunal is a skill for Claude Code from aegntic/cldcde. It costs 54 tokens per session (1,286 once invoked), scanned A, original, MIT.

A three-agent review process for finding security, logic, usability, and performance problems in code. The agents take different roles and must agree before approving the code.

In plain words
What is it for?
Use it to review critical changes, audit security, test invalid or confusing user flows, inspect performance bottlenecks, and validate pull requests.
Why use it?
A single review can miss problems from another perspective. Separate security, user-behavior, and performance checks provide broader validation before a change is merged.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

This is aegntic/cldcde's own configuration. It tells Claude Code how to work on cldcde itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cldcde configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 /a0/usr/plugins/red-team-tribunal/red-team-tribunal.py --target <file>.

Reuse

Borrowing it

Nothing to install: this file belongs to aegntic/cldcde. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/aegntic/cldcde/main/.claude/skills/red-team-tribunal/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/aegntic/cldcde

Made for: Claude Code.

Wrote 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.

agentmods badge for red-team-tribunal

README.md
[![agentmods](https://agentmods.dev/badge/skills/aegntic/cldcde/red-team-tribunal/github.svg)](https://agentmods.dev/skills/aegntic/cldcde/red-team-tribunal)
Your own site
<a href="https://agentmods.dev/skills/aegntic/cldcde/red-team-tribunal"><img src="https://agentmods.dev/badge/skills/aegntic/cldcde/red-team-tribunal/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.

agentmods 80×15 button for red-team-tribunal

Your own site · 80×15
<a href="https://agentmods.dev/skills/aegntic/cldcde/red-team-tribunal"><img src="https://agentmods.dev/badge/skills/aegntic/cldcde/red-team-tribunal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,286 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00054 $0.01286
Opus 5 $0.00027 $0.00643
Sonnet 5 $0.00011 $0.00257
Haiku 4.5 $0.00005 $0.00129

Measured 10d ago against content hash bd9b0e2f2679, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

red-team-tribunal scanned grade A 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 10d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

subprocess.run(..., timeout=120) # 2 minutes
.claude/skills/red-team-tribunal/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Red Team Tribunal: Adversarial Verification

Overview

The Red Team Tribunal uses Opus 4.6 Agent Teams to create an adversarial review loop that prevents "confident mistakes." Three specialized sub-agents work in parallel to find issues from different perspectives.

The Tribunal Structure

🤔 The Skeptic (Security/Logic)

  • Role: Security auditor and logic validator
  • Goal: Find at least one valid issue (must find something)
  • Focus: Security flaws, logic errors, edge cases, race conditions
  • Confidence Target: >80%

👤 The User Proxy (UX/Edge Cases)

  • Role: End-user simulator
  • Goal: Break the feature from a user's perspective
  • Focus: Usability, invalid inputs, confusing flows, accessibility
  • Tools: Browser automation, form fuzzing

⚡ The Optimizer (Performance)

  • Role: Performance engineer
  • Goal: Identify efficiency bottlenecks
  • Focus: Algorithmic complexity, memory usage, database queries, caching
  • Metrics: O(n) complexity, response times, resource usage

When to Use

Activate the Tribunal for:

  • Critical code changes (auth, payments, security)
  • Before merging pull requests
  • When adding new features
  • Security-sensitive implementations
  • Performance-critical code
  • Code that affects multiple users

Usage

Trigger Tribunal Review

# Review a file
python3 /a0/usr/plugins/red-team-tribunal/red-team-tribunal.py --target <file>

# Review a PR
python3 /a0/usr/plugins/red-team-tribunal/red-team-tribunal.py --pr <number>

# Review a commit
python3 /a0/usr/plugins/red-team-tribunal/red-team-tribunal.py --diff <hash>

Understanding Verdicts

CONSENSUS OPTIONS:

  1. APPROVED (All agents pass)

    • Code meets all quality standards
    • Ready to merge
  2. CONDITIONAL (Concerns raised)

    • Minor issues found
    • Address concerns before merge
    • Can proceed with fixes
  3. REJECTED (Critical issues)

    • Security vulnerabilities or major flaws
    • Must fix before reconsideration
    • Returns detailed recommendations

Read the full file on GitHub · 180 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. 10d ago First seen · 180 lines · 54 tokens per session scan A bd9b0e2f2679

Subscribe to this mod's changes

red-team-tribunal is a skill published in the GitHub repository aegntic/cldcde (11 stars, last pushed 13d ago), licensed MIT. It adds 54 tokens to every session and 1,286 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

audit

Use when the user wants a code review on recent changes — quality, spec, security, or performance feedback. Triggers a multi-level (L1-L5) review with a standalone Reviewer; on NEEDSFIX, offers to apply findings via /hyperflow:plan. Trigger with /hyperflow:audit, "review this change", "review my PR", "audit the diff"…

jeremylongshore/tons-of-skills-marketplace · 84 tokens

quality-gate

Orchestrates the QUALITY pipeline stage for egregore work items, running code review, unbloat, and test updates. Use when running quality checks before a PR.

athola/claude-night-market · 39 tokens

plugin-review

Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.

athola/claude-night-market · 23 tokens

plugin-quality

A review guide for checking Zhin.js plugins before release. It covers plugin structure, feature declarations, resource cleanup, message sending, and security.

zhinjs/zhin · 49 tokens

architecture-review

Agents should invoke this skill for architecture reviews, module boundaries, dependency direction, coupling/cohesion, SOLID concerns, system design trade-offs, layering, service boundaries, or design decisions before implementation.

Firstp1ck/pi-coding-agent-forge · 43 tokens

spec-vs-impl-checker

Agents should invoke this skill when a spec, plan, README, issue, or requirement must be verified against implementation. Traces requirements to code, checks interface contracts, and reports gaps or mismatches.

Firstp1ck/pi-coding-agent-forge · 48 tokens