reproducibility-validate

reproducibility-validate is a skill for Claude Code, Codex from jmagly/aiwg. It costs 25 tokens per session (1,602 once invoked), scanned A, original, MIT.

A workflow check that runs the same process multiple times and compares its outputs.

In plain words
What is it for?
It produces a similarity score and a pass-or-fail verdict, with options for the number of runs and the required similarity threshold.
Why use it?
It shows whether a workflow is consistent between runs, which helps reveal nondeterministic results.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It produces a similarity score and a pass-or-fail verdict, with options for the number of runs and the required similarity threshold.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jmagly/aiwg/reproducibility-validate
Install

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.

Any agent
npx skills add jmagly/aiwg --skill reproducibility-validate
Clone the repo
git clone --depth 1 https://github.com/jmagly/aiwg

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for reproducibility-validate

README.md
[![agentmods](https://agentmods.dev/badge/skills/jmagly/aiwg/reproducibility-validate.svg)](https://agentmods.dev/skills/jmagly/aiwg/reproducibility-validate)
Your own site
<a href="https://agentmods.dev/skills/jmagly/aiwg/reproducibility-validate"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/reproducibility-validate.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,602 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 180
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 181
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.01602
Opus 5 $0.00013 $0.00801
Sonnet 5 $0.00005 $0.00320
Haiku 4.5 $0.00003 $0.00160

Measured 4d ago against content hash c3bab5bb9efe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

reproducibility-validate 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 4d 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.

agentic/code/addons/aiwg-utils/skills/reproducibility-validate/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reproducibility Validate

You run a workflow multiple times and compare outputs to produce a similarity score and pass/fail verdict, confirming that the workflow produces consistent results across executions.

Triggers

Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):

  • "is this workflow stable" → run reproducibility validation with defaults
  • "check if results are consistent" → run reproducibility validation
  • "does this run the same way every time" → run reproducibility validation
  • "test determinism" → run reproducibility validation
  • "compare workflow outputs" → run reproducibility validation

Trigger Patterns Reference

Pattern Example Action
Default validation "validate reproducibility of onboarding-flow" Run aiwg reproducibility-validate onboarding-flow
Custom run count "validate with 5 runs" Run aiwg reproducibility-validate <id> --runs 5
Custom threshold "validate with 99% threshold" Run aiwg reproducibility-validate <id> --threshold 0.99
Full options "3 runs, 90% threshold" Run aiwg reproducibility-validate <id> --runs 3 --threshold 0.90

Behavior

When triggered:

  1. Extract intent:

    • What is the workflow ID or name to validate?
    • How many runs? (default: 3)
    • What similarity threshold must be met to pass? (default: 0.95)
  2. Run the command:

    # Default: 3 runs, 0.95 threshold
    aiwg reproducibility-validate <workflow-id>
    
    # Custom run count
    aiwg reproducibility-validate <workflow-id> --runs 5
    
    # Custom threshold
    aiwg reproducibility-validate <workflow-id> --threshold 0.99
    
    # Both
    aiwg reproducibility-validate <workflow-id> --runs 5 --threshold 0.99
    
  3. Scoring method:

    • Structured outputs (JSON, YAML): exact match required — score is 0 or 1 per artifact
    • Text outputs (Markdown, prose): semantic similarity score (0.0–1.0) computed across runs
    • Overall score: weighted average across all artifacts in the workflow

Read the full file on GitHub · 182 lines

Changes

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.

  1. 4d ago First seen · 182 lines · 25 tokens per session scan A c3bab5bb9efe

Subscribe to this mod's changes

reproducibility-validate is a skill published in the GitHub repository jmagly/aiwg (209 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 1,602 once invoked, about $0.0001 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 2026-09-03.

Related

Other skills, from other repositories

testing-patterns

Comprehensive testing patterns for Jest, Vitest, Playwright, and React Testing Library. Use when writing unit tests, integration tests, or E2E tests.

Wania-Kazmi/claude-code-autonomous-agent-workflow · 37 tokens

verify

Runs this project's check chain through scripts/verify.py and reads the receipt it writes. Fires when tracked changes are finished, when the user asks whether work passes, before a commit, and before reporting a task done. Stays dormant in repositories with no detectable check chain, during read-only audits, and for…

cwinvestments/memstack · 71 tokens

go-test-review

Review Go test code for quality including table-driven tests, t.Helper usage, assertion completeness, boundary cases, benchmarks, fuzz tests, and coverage targets. Trigger when PR contains test.go files, test helpers, httptest usage, testing.B, testing.F, or testdata directories. Use for test-quality focused review.

johnqtcg/awesome-skills · 68 tokens

kdd-test-coverage-scan

Guia a cualquier agente (no depende de ningun modelo puntual) para producir un scan de gaps de cobertura de tests (rutas criticas sin cubrir, casos de error sin test, regresiones sin atrapar) en el formato de contrato de Capa 3 de KDD -- findings.json -- que despues gatea scripts/validatetestcoveragefindings.py. Usala…

MauricioPerera/KDD · 167 tokens

jacoco

Check JaCoCo code coverage for a Maven/Java project against a gate, then drill into per-module, per-class, and per-line gaps to target tests. Use when the user says "what's our test coverage", "check coverage", "which classes need tests", "are we above the coverage gate", or is planning tests to reach a threshold.

alexmond/alexmskills · 75 tokens

testing

Strategy and rules for writing or improving automated tests. Use when adding tests, improving coverage, fixing flaky tests, setting up a test suite, or deciding what and how to test. Emphasizes deterministic tests, testing behavior over implementation, and a tight validation loop. For diagnosing production failures…

thixpin/pitway · 85 tokens