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.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.00310 |
| Sonnet 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 7d 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.
- 7d 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 2mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 620 once invoked, about $0.0002 per session on Opus 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.
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…
local-paper-navigator
Find and read papers from the local papers library (repo papers/, mounted at /papers/). Three native tools form a reading funnel: papersearch (one line per paper), paperread (card + section outline), papersection (one verbatim section — the only full-text access). Use when: find papers in the local library, read a…
experiment-pipeline
Guides structured 4-stage experiment execution with attempt budgets and gate conditions: Stage 1 initial implementation (reproduce baseline), Stage 2 hyperparameter tuning, Stage 3 proposed method validation, Stage 4 ablation study. Integrates with evo-memory (load prior strategies, trigger IVE/ESE) and…
paper-review
Guides self-review of YOUR OWN academic paper before submission with adversarial stress-testing. Core method: 5-aspect checklist (contribution sufficiency, writing clarity, results quality, testing completeness, method design), counterintuitive protocol (reject-first simulation, delete unsupported claims, score trust…