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 jdpalumbo2/workbench --skill red-team-pressure-testgit clone --depth 1 https://github.com/jdpalumbo2/workbenchWrote 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/jdpalumbo2/workbench/red-team-pressure-test)<a href="https://agentmods.dev/skills/jdpalumbo2/workbench/red-team-pressure-test"><img src="https://agentmods.dev/badge/skills/jdpalumbo2/workbench/red-team-pressure-test/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/jdpalumbo2/workbench/red-team-pressure-test"><img src="https://agentmods.dev/badge/skills/jdpalumbo2/workbench/red-team-pressure-test.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 | $0.00045 | $0.00802 |
| Opus 5 | $0.00023 | $0.00401 |
| Sonnet 5 | $0.00009 | $0.00160 |
| Haiku 4.5 | $0.00005 | $0.00080 |
Grade A, and why
red-team-pressure-test 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 8d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Red Team Pressure Test
Overview
The work isn't finished until someone has tried to destroy it. Dispatch an adversary whose only job is to find every gap, loophole, and weak assumption — ruthlessly, not softened.
When to Use
- About to present a plan, launch something, or defend a position, and want to hear every gap from a fresh source before someone in the room finds it.
- High-stakes decision where being wrong is expensive: a contract, a client-facing plan, a change to a production automation.
Not for: quick low-stakes checks — the point of this skill is genuine independence, which costs a subagent dispatch. Don't reach for it on something that doesn't warrant that cost. Also not for a code change or build plan that already runs through a dedicated review lane (a clodex/TRIP-style pipeline, a codex-plan-review/codex-code-review pass) — those exist precisely so code doesn't need this skill on top. This is for the plans and decisions with no other adversarial pass built in: strategy, pitches, contracts, anything client-facing or belief-shaped rather than code-shaped.
Core Pattern
Self-critique from the same context that produced the plan is weak — it's anchored on the reasoning that already convinced itself the plan was good. Real adversarial pressure needs a fresh, independent pass with no investment in the plan succeeding.
- State the plan or claim in full, exactly as it would be presented, with no framing that pre-defends it.
- Dispatch a subagent via the Agent tool with an explicitly adversarial brief: its only goal is to find every gap, loophole, and weak assumption, and to be ruthless about it — not to also list what's good. Give it the plan verbatim; don't summarize it into your own words first, or it'll end up interrogating your paraphrase instead of the plan.
- Return the subagent's findings as a structured list — gaps, weak assumptions, failure points — not folded into a diplomatic paragraph. If a finding is weak or a stretch, keep it in the list rather than pre-filtering; the person using this decides what to act on.
What ships with it
1 file 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.
- 8d ago First seen · 42 lines · 45 tokens per session scan A 10472d5eb0c2
red-team-pressure-test is a skill published in the GitHub repository jdpalumbo2/workbench (1 stars, last pushed 5d ago), licensed MIT. It adds 45 tokens to every session and 802 once invoked, about $0.0002 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.
Other skills, from other repositories
code-review-excellence
This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
architecture-design
Use only when creating new registrable ML components that require Factory or Registry patterns.
results-analysis
This skill should be used when the user asks to "analyze experimental results", "run strict statistical analysis", "compare model performance", "generate scientific figures", "check significance", "do ablation analysis", or mentions interpreting experiment data with rigorous statistics and visualization. It focuses on…
review-response
Systematic review response workflow from comment analysis to professional rebuttal writing. Use when the user asks to "write rebuttal", "respond to reviewers", "draft review response", or "analyze review comments". Improves paper acceptance rates.
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.