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 Agent-Engineer-Master/skill-engineer --skill stress-testgit clone --depth 1 https://github.com/Agent-Engineer-Master/skill-engineerWrote 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/agent-engineer-master/skill-engineer/stress-test)<a href="https://agentmods.dev/skills/agent-engineer-master/skill-engineer/stress-test"><img src="https://agentmods.dev/badge/skills/agent-engineer-master/skill-engineer/stress-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/agent-engineer-master/skill-engineer/stress-test"><img src="https://agentmods.dev/badge/skills/agent-engineer-master/skill-engineer/stress-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 | $0.00109 | $0.01691 |
| Opus 5.5 | $0.00044 | $0.00676 |
| Sonnet 5.5 | $0.00022 | $0.00338 |
| Haiku 4.5 | $0.00011 | $0.00169 |
Grade A, and why
stress-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 1mo 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/stress-test — Strategic Decision Analysis
Runs a three-phase decision analysis using verbalized sampling to surface tail-distribution insights — the non-obvious analyses that standard prompting suppresses.
Usage:
/stress-test should I enter the home wellness category or stay narrower?/stress-test two content formats: long-form carousel vs short-form daily posts/stress-test hire a contractor now vs wait until revenue hits $10k/mo
Background
After alignment training (RLHF/DPO), LLMs suffer from mode collapse: they return the most typical analysis — safe, expected, rarely wrong but rarely surprising. The genuinely valuable insights live in the tails of the distribution.
Verbalized sampling (Zhang et al., Stanford 2025) fixes this: by asking the model to generate multiple candidate responses with probability estimates, it forces reasoning across the full distribution, including the suppressed tails. Diversity gains of 1.6–2.1x in creative tasks have been reported.
Important caveat (from follow-up research, Jun 2025): The probability numbers are unreliable — LLMs can describe a distribution accurately but don't faithfully sample from it. The mechanism that actually works is the diversity forcing (generate N, select from the non-obvious end), not the precision of the scores. Use the scores as a ranking device, not a measurement.
Step 0 — Load Context
Before running the analysis, read the relevant context files for this project:
- Your personal/founder context file — profile, constraints, time/financial constraints
- Your constraints file — hard constraints on any decision
- Your anti-goals or strategic boundaries file
- If a product/store decision: your store or product context file
- If a brand/content decision: your brand summary file
Adjust these paths to match your project structure. The goal is grounding the analysis in real constraints before reasoning begins.
Reframe the question if needed after reading context (e.g. "build vs buy" might actually be "delegate vs own").
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.
- 1mo ago First seen · 143 lines · 109 tokens per session scan A 621401512b67
stress-test is a skill published in the GitHub repository Agent-Engineer-Master/skill-engineer (8 stars, last pushed 3mo ago), licensed MIT. It adds 109 tokens to every session and 1,691 once invoked, about $0.0004 per session on Opus 5.5. 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
openspec-verify-change
Verify implementation matches OpenSpec change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving. Also use when the user says "openspec verify" or "opsx verify".
openspec-new-change
Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach. Also use when the user says "openspec new change" or "opsx new".
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.