regulated-mcp-insurance-deployment: Skill for Claude Code

.agents/skills/reproducible-evals/SKILL.md

reproducible-evals is a skill for Claude Code, Codex from waalwalker1/regulated-mcp-insurance-deployment. It costs 24 tokens per session (98 once invoked), scanned A, original, MIT.

A method for creating repeatable software evaluations, also called benchmarks, from versioned datasets and code. It records how data is split, how results are measured, and which environment produced them.

In plain words
What is it for?
Building evaluation datasets, running seeded benchmarks, recording model and environment details, saving raw results, generating summaries, and reviewing failure examples.
Why use it?
It makes evaluation results easier to reproduce and compare. Reports are generated from recorded results instead of being changed manually.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is waalwalker1/regulated-mcp-insurance-deployment's own configuration. It tells Claude Code and Codex how to work on regulated-mcp-insurance-deployment itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything regulated-mcp-insurance-deployment configures →

Reuse

Borrowing it

Nothing to install: this file belongs to waalwalker1/regulated-mcp-insurance-deployment. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/waalwalker1/regulated-mcp-insurance-deployment/main/.agents/skills/reproducible-evals/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/waalwalker1/regulated-mcp-insurance-deployment

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 reproducible-evals

README.md
[![agentmods](https://agentmods.dev/badge/skills/waalwalker1/regulated-mcp-insurance-deployment/reproducible-evals/github.svg)](https://agentmods.dev/skills/waalwalker1/regulated-mcp-insurance-deployment/reproducible-evals)
Your own site
<a href="https://agentmods.dev/skills/waalwalker1/regulated-mcp-insurance-deployment/reproducible-evals"><img src="https://agentmods.dev/badge/skills/waalwalker1/regulated-mcp-insurance-deployment/reproducible-evals/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.

agentmods 80×15 button for reproducible-evals

Your own site · 80×15
<a href="https://agentmods.dev/skills/waalwalker1/regulated-mcp-insurance-deployment/reproducible-evals"><img src="https://agentmods.dev/badge/skills/waalwalker1/regulated-mcp-insurance-deployment/reproducible-evals.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 98 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.
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 $0.00024 $0.00098
Opus 5 $0.00012 $0.00049
Sonnet 5 $0.00005 $0.00020
Haiku 4.5 $0.00002 $0.00010

Measured 11d ago against content hash f03c6739c9a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

reproducible-evals 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 11d 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.

.agents/skills/reproducible-evals/SKILL.md · 21 lines

What it actually says

Reproducible Evals

All benchmarks must have:

  • dataset/fixture version;
  • random seed;
  • split methodology;
  • metric definitions;
  • environment/model/provider metadata;
  • timestamp;
  • raw machine-readable results;
  • generated Markdown summary;
  • failure examples.

Never edit metric tables by hand. Reports must be regenerated by one documented command.

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. 11d ago First seen · 21 lines · 24 tokens per session scan A f03c6739c9a9

Subscribe to this mod's changes

reproducible-evals is a skill published in the GitHub repository waalwalker1/regulated-mcp-insurance-deployment (0 stars, last pushed 21d ago), licensed MIT. It adds 24 tokens to every session and 98 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 2026-08-31.

Related

Other skills, from other repositories

api-testing

Testing patterns for MCP tool/resource handlers using createMockContext and Vitest. Covers mock context options, handler testing, McpError assertions, format testing, Vitest config setup, and test isolation conventions.

cyanheads/obsidian-mcp-server · 46 tokens

add-test

Scaffold a test file for an existing tool, resource, or service. Use when the user asks to add tests, improve coverage, or when a definition exists without a matching test file.

cyanheads/obsidian-mcp-server · 41 tokens

email-formatting

Markdown formatting conventions for email summary documents — heading depth, list style, line length, emoji policy, and a mandatory provenance footer. Read this when producing a markdown report that summarizes one or more email messages so the output matches the project's house style.

provos/ironcurtain · 53 tokens

json-schema-emails

Canonical shape of the .workflow/emails/emails.json file passed between the fetch and summarize states — required fields (sender, recipient, subject, date, body), types, and field semantics. Read this whenever you write or read emails.json so producer and consumer agree on the shape.

provos/ironcurtain · 62 tokens

test-writing

Write test output, harnesses, and assertions in the terse Unix tradition. Covers Rust #[test], Go testing.T, Python pytest, typed CLI harnesses, and CI integration. Use when writing new tests, test harnesses, CI profiles, or reviewing test output verbosity.

Kevin-Liu-01/Agent-Machines · 58 tokens

testing-rate-limiting

Apply deterministic SlowAPI rate-limiter isolation for FastAPI transport tests, especially to avoid flaky HTTP 429 responses.

asap-protocol/asap-protocol · 29 tokens