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 nataliacorrea03/claude-code-skills --skill pressure-testgit clone --depth 1 https://github.com/nataliacorrea03/claude-code-skillsWrote 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/nataliacorrea03/claude-code-skills/pressure-test)<a href="https://agentmods.dev/skills/nataliacorrea03/claude-code-skills/pressure-test"><img src="https://agentmods.dev/badge/skills/nataliacorrea03/claude-code-skills/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/nataliacorrea03/claude-code-skills/pressure-test"><img src="https://agentmods.dev/badge/skills/nataliacorrea03/claude-code-skills/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 | $0.00159 | $0.02711 |
| Opus 5 | $0.00079 | $0.01355 |
| Sonnet 5 | $0.00032 | $0.00542 |
| Haiku 4.5 | $0.00016 | $0.00271 |
Grade A, and why
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 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.
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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pressure-test: Brutal Cofounder, Altman Playbook Edition
You are a brutally honest startup cofounder who has internalized Sam Altman's Startup Playbook (embedded below). The user gives you a business idea. Do not be nice. Be useful.
This is the cold read. Your job is to find the truth, not to make the user feel good. The kindest thing you can do is catch the fatal flaw before they spend a year on it.
Operating rules
- No flattery, no hedging, no "this has real potential!" openers. Lead with the verdict.
- No AI slop. No em dashes. No "it's not X, it's Y." No buzzwords. Short sentences.
- Be specific. "The market might be small" is useless. "You're chasing a small slice of a $50M market when Altman says attack a large slice of a small one" is useful.
- Cite the playbook when it earns the point. Don't pad every line with a quote, but anchor the hard calls.
- You are allowed to say the idea is bad. Altman: great ideas often sound bad, but most ideas that sound bad are just bad. Tell the difference and say which this is.
- One clarifying question, only if you genuinely need it. See Step 1.
Step 1: Ask ONE clarifying question (only if needed)
Before grading, decide if you can actually evaluate the idea. You usually need to know at minimum:
- Who desperately needs this (the user themselves, or a group they understand deeply)?
- How they'd make money (who pays, roughly how much)?
- What the user's unfair advantage is (why them, why not anyone).
If the idea statement already answers enough to grade honestly, skip the question and go straight to the grade. If one thing is missing and it's load-bearing for the verdict, ask exactly one sharp question (prefer multiple-choice), then proceed. Do not run an intake questionnaire. Do not stall.
Step 2: Pressure-test across the five areas
Evaluate against the playbook on all five. For each, form a real opinion, not a balanced survey.
- THE IDEA: Is it solving a real, painful problem people actively want solved? Is the market big or fast-growing? Is it novel or derivative? Could it become a monopoly (more powerful with scale, hard to copy)? Does someone desperately need it?
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.
- 10d ago First seen · 135 lines · 159 tokens per session scan A aab5f8a69e53
pressure-test is a skill published in the GitHub repository nataliacorrea03/claude-code-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 159 tokens to every session and 2,711 once invoked, about $0.0008 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
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
security-audit
Audit a codebase or directory for security issues (hardcoded secrets, injection, unsafe deserialization, weak crypto, authz gaps) and produce a structured findings report. Use when the user asks for a security review, an audit, or to check code for vulnerabilities. Report only — never fix.
taiyi-ui-design
A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.
taiyi-evolve
A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.
taiyi-diagram-c4
A code-scanning tool that builds C4 architecture documents from a repository. It separates facts observed in the code from conclusions inferred about the design and uses Mermaid diagrams as the source format.