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 yogsoth-ai/stress-test --skill failure-anticipationgit clone --depth 1 https://github.com/yogsoth-ai/stress-testWrote 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/yogsoth-ai/stress-test/failure-anticipation)<a href="https://agentmods.dev/skills/yogsoth-ai/stress-test/failure-anticipation"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/failure-anticipation/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/yogsoth-ai/stress-test/failure-anticipation"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/failure-anticipation.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 | $0.00065 | $0.01262 |
| Opus 5 | $0.00032 | $0.00631 |
| Sonnet 5 | $0.00013 | $0.00252 |
| Haiku 4.5 | $0.00006 | $0.00126 |
Grade A, and why
failure-anticipation 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Failure Anticipation Campaign
Core question: If this artifact fails, how will it fail?
Methodology Sources
- Klein (2007) — Pre-Mortem technique: assume failure, retrospect causes
- AIAG-VDA FMEA Handbook (2019) — 7-step FMEA with Action Priority
- IEC 60812 — Failure modes and effects analysis standard
Strategy Routing
| Artifact Type | Primary Strategy | Fallback Strategy |
|---|---|---|
| hypothesis, claim | prospective-hindsight | design-fmea |
| research-question | design-fmea | process-fmea |
| idea, approach | design-fmea | prospective-hindsight |
| experiment-design | process-fmea | design-fmea |
| gap | risk-prioritization | prospective-hindsight |
Budget Table
| Parameter | S (Quick) | M (Standard) | L (Deep) |
|---|---|---|---|
| Failure modes | 8 | 20 | 40 |
| Failure chain depth | 2 | 4 | 6 |
| Mitigation measures | 3 | 8 | 15 |
| Re-scoring rounds | 1 | 2 | 3 |
Tactics
- premortem-to-fmea-pipeline — Pre-mortem screens, high-risk items trigger full FMEA
- failure-chain-tracing — Trace upstream causes and downstream effects
- mitigation-validation — Mini-FMEA on proposed mitigations to verify no new risks
Context Management
Each subagent operates in isolated context. Pre-mortem facilitation runs first to generate rapid failure scenarios. High-severity items are passed to FMEA subagents for structured analysis. Severity/Occurrence/Detection scores flow through action-priority-matrix for classification. Mitigations are validated via re-scoring loop.
Output
Produces FailureAnticipationReport containing: failure mode catalog, cause-effect chains, S/O/D scores, action priority classification (H/M/L), mitigation measures, and post-mitigation re-scores.
Available Strategies
Optional, no fixed order; the final leaf is always a sop.
| Strategy | When to use |
|---|---|
| design-fmea | Strategy: Research design-level FMEA — function analysis, failure mode identification, severity/occurrence/detection scoring per AIAG-VDA 2019. |
| mitigation-design | Strategy: Design prevention, detection, and response measures for high-priority failure modes. Produces actionable countermeasures validated via re-scoring. |
| process-fmea | Strategy: Research execution process FMEA — analyzes how the research process itself can fail during execution, distinct from design-level failures. |
| prospective-hindsight | Strategy: Klein pre-mortem — assume the artifact has failed, then retrospect plausible causes. Generates rapid failure scenario catalog. |
| risk-prioritization | Strategy: Action Priority matrix — classifies failure modes into H/M/L priority using severity-weighted scoring per AIAG-VDA 2019 Action Priority tables. |
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 · 115 lines · 65 tokens per session scan A bd12dc43b9a7
failure-anticipation is a skill published in the GitHub repository yogsoth-ai/stress-test (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,262 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 2026-08-31.
Other skills, from other repositories
tournament-judge
Runs a domain-neutral, evidence-based tournament in which independent candidates are reviewed, anonymized, and scored by a blind judge against a rubric fixed before judging. Use when comparing competing plans, designs, implementations, documents, tools, vendors, strategies, or other substantial options; when the user…
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
browser_cdp
A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
creating-skills
Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, update an existing skill, or needs skill creation guidelines. Provides structure, frontmatter fields, naming conventions, and new features like dynamic context…
config-validator
Validate AIWG configuration files and project setup for correctness and completeness.