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 causal-necessity-testinggit 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/causal-necessity-testing)<a href="https://agentmods.dev/skills/yogsoth-ai/stress-test/causal-necessity-testing"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/causal-necessity-testing/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/causal-necessity-testing"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/causal-necessity-testing.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 | $0.00039 | $0.00620 |
| Opus 5.5 | $0.00016 | $0.00248 |
| Sonnet 5.5 | $0.00008 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
causal-necessity-testing 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.
This is a copy
100% identical to causal-necessity-testing — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Causal Necessity Testing Tactic
PNS evaluation: for each causal claim, determine whether the cause is necessary, sufficient, both, or neither.
Orchestration
- causal-claim-extraction extracts all X→Y causal claims from the artifact
- necessity-evaluation asks: if X had NOT occurred, would Y still hold? (PN)
- sufficiency-evaluation asks: if X occurred in isolation, would Y follow? (PS)
- Classify each claim into quadrant:
- PN high + PS high → INUS condition (load-bearing)
- PN high + PS low → necessary but not sufficient
- PN low + PS high → sufficient but redundant
- PN low + PS low → spurious or decorative
- load-bearing-identification synthesizes quadrant assignments
Scoring
- PN and PS scored 0.0–1.0 (probability estimates)
- Threshold for "high": >= 0.7
- Threshold for "low": < 0.3
- Middle range (0.3–0.7): uncertain, flag for deeper investigation
Subagents Dispatched
- causal-claim-extraction (claim identification)
- necessity-evaluation (PN scoring per claim)
- sufficiency-evaluation (PS scoring per claim)
- load-bearing-identification (quadrant synthesis)
Termination Conditions
- All extracted claims evaluated within budget
- Early termination if INUS condition found and budget is S
- All claims score PN < 0.3 (no necessary factors found — conclusion may be overdetermined)
Available SOPs
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use |
|---|---|
| causal-claim-extraction | Extract all causal claims (X causes Y, X leads to Y, X enables Y) from an artifact, producing a structured list of cause-effect pairs. |
| load-bearing-identification | Identify which factors are "load-bearing walls" — factors whose removal would collapse the conclusion. |
| necessity-evaluation | Evaluate the probability of necessity (PN) for a causal factor — would the conclusion fail if this factor were absent? |
| sufficiency-evaluation | Evaluate the probability of sufficiency (PS) for a causal factor — would this factor alone be enough to produce the conclusion? |
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 · 68 lines · 39 tokens per session scan A 29a317fced6d
causal-necessity-testing is a skill published in the GitHub repository yogsoth-ai/stress-test (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 620 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to causal-necessity-testing, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
relax-dev-debug
Develop and debug the Relax reinforcement learning project. Use this skill whenever modifying code in the relax/ directory, or running remote training jobs on a Ray cluster for validation. Also use it when the user mentions training, debugging training runs, submitting Ray jobs, or fixing training errors.
access-gevety-health-biomarker-data
Access your Gevety health data - biomarkers, healthspan scores, biological age, supplements, activities, daily actions, 90-day health protocol, and upcoming tests.
aminer-open-academic-search
ACADEMIC PRIORITY: Activate this skill whenever the user's query involves academic, scholarly, or research-related topics — including but not limited to: papers, publications, citations, scholars, researchers, professors, institutions, universities, labs, journals, conferences,…
acorn-theorem-prover-verifier
Verify and write proofs using the Acorn theorem prover for mathematical and cryptographic formalization. Use when working with Acorn proof files (.ac), verifying theorems, formalizing mathematical or cryptographic protocols, or writing proofs in the Acorn language. Triggers on:…
research-ideation
Quant-focused research ideation pipeline: scope selection (3 stages) → anchor-first literature grounding → single-core idea generation → iterative refinement → ELO tournament ranking (Final = N+R+C−D) → update evo-memory → user selects direction → expand into manuscript-quality proposal. Optimized for incremental…
quant-experiment-runtime
Quant research experiment executor: discover an offline source database under the workdir's code-repo, build a panel, run a Research Artifact's entry point to compute research-object values, and evaluate IC/ICIR/RANKIC/coverage metrics. Runtime = Experiment Executor; it runs a Research Artifact via a Python-native…