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 skills add CarbeneAI/Forge --skill redteamgit clone --depth 1 https://github.com/CarbeneAI/ForgeWrote 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/skills/carbeneai/forge/redteam)<a href="https://agentmods.dev/skills/carbeneai/forge/redteam"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/redteam/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/skills/carbeneai/forge/redteam"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/redteam.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 | $0.00059 | $0.01185 |
| Opus 5 | $0.00030 | $0.00593 |
| Sonnet 5 | $0.00012 | $0.00237 |
| Haiku 4.5 | $0.00006 | $0.00119 |
Grade A, and why
RedTeam 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RedTeam
Adversarial analysis system using parallel agents to rigorously challenge ideas, proposals, and strategies from multiple attack vectors.
Methodology
The RedTeam skill deploys 3-5 parallel agents, each taking a different adversarial perspective to stress-test your ideas. Instead of confirmation bias, you get multi-angle critique designed to expose weaknesses before they become failures.
Attack Vectors
Each agent attacks from a different angle:
- Technical Feasibility - Can this actually be built? What technical debt, dependencies, or implementation gaps exist?
- Market Risk - Will anyone care? What competitive threats, market timing issues, or adoption barriers exist?
- Resource Constraints - Do you have the time, money, people, and skills to execute?
- Hidden Assumptions - What unstated beliefs underpin this plan? Which assumptions are fragile?
- Second-Order Effects - What unintended consequences, downstream impacts, or ripple effects could emerge?
Severity Scoring
Findings are rated on a 5-point scale:
- CRITICAL (5) - Fatal flaw. Project will likely fail without addressing this.
- HIGH (4) - Serious risk. Strongly recommend mitigation before proceeding.
- MEDIUM (3) - Moderate concern. Address during planning or early implementation.
- LOW (2) - Minor issue. Monitor but not blocking.
- INFO (1) - Observation for awareness. No immediate action required.
Output Format
The synthesis produces:
- Executive Summary - Top 3-5 vulnerabilities identified
- Findings by Severity - All issues grouped by score
- Recommended Mitigations - Specific actions to address each finding
- Go/No-Go Assessment - Clear recommendation on whether to proceed
Workflow Routing
| Workflow | Trigger | File |
|---|---|---|
| Adversarial Analysis | "red team this", "stress test", "poke holes" | workflows/AdversarialAnalysis.md |
| Claim Decomposition | "analyze argument", "check logic", "find fallacies" | workflows/ClaimDecomposition.md |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 122 lines · 59 tokens per session scan A 102d3484201f
RedTeam is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 1,185 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 2026-09-03.
Other skills, from other repositories
anti-debug-bypass
Detect and neutralize anti-debug / anti-VM checks — IsDebuggerPresent, ptrace, NtGlobalFlag, timing, hardware-breakpoint detection.
malware-triage
Fast malware triage workflow — static (PE/Mach-O/ELF format, strings, imports, signatures, entropy/packed indicators), dynamic (sandbox with INetSim, Wireshark, Process Monitor, Procmon, time-shift), unpack (Scylla/PE-sieve), then full RE with Ghidra/IDA. Designed for ≤15 min initial verdict.
packer-unpacking
Identify and unpack common binary packers — UPX, ASPack, Themida, VMProtect, MPRESS, PECompact, Enigma.
lint-and-fix
Run linters and fix violations, formatting errors, or style mismatches using Trunk. Use when code quality checks fail, before submitting PRs, or to repair "broken" linting states.
test-and-fix
Run unit tests and automatically fix code failures, regression bugs, or test mismatches. Use when tests are failing, after implementing new features, or to repair "broken" tests.
ghidra
Deep binary analysis via Ghidra — headless analyzeHeadless or live MCP bridge with 245 tools. Decompilation, xrefs, function listing, batch operations, P-code emulation, convention enforcement.