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.
git clone --depth 1 https://github.com/wan-huiyan/claude-ecosystem-hygieneWrote 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/plugins/wan-huiyan/claude-ecosystem-hygiene/ab-harness)<a href="https://agentmods.dev/plugins/wan-huiyan/claude-ecosystem-hygiene/ab-harness"><img src="https://agentmods.dev/badge/plugins/wan-huiyan/claude-ecosystem-hygiene/ab-harness/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/plugins/wan-huiyan/claude-ecosystem-hygiene/ab-harness"><img src="https://agentmods.dev/badge/plugins/wan-huiyan/claude-ecosystem-hygiene/ab-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ab-harness 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 8d 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.
What it actually says
{
"name": "ab-harness",
"description": "Counterfactual A/B + layered-ablation harness for Claude Code setup. Measures whether your ~/.claude/ stack (skills, lessons, axioms, memory) plus in-repo discipline (docs/runbooks, decisions, findings) actually helps on real tasks. Binary A/B (setup-ON vs setup-OFF) and layered ablation (strip one layer at a time, rank by impact). Heavyweight: $10\u2013$80 per run, 30min\u20133hrs wall time \u2014 this is a measurement experiment, not a lint. Pairs with ecosystem-audit (identify HOT artifacts) and memory-hygiene (prune DORMANT ones).",
"version": "1.2.0",
"author": {
"name": "wan-huiyan",
"url": "https://github.com/wan-huiyan"
},
"repository": "https://github.com/wan-huiyan/claude-ecosystem-hygiene",
"license": "MIT",
"keywords": [
"claude-code",
"claude-code-skill",
"ab-testing",
"ablation",
"counterfactual",
"measurement",
"hygiene",
"ecosystem"
]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 199 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 8d ago First seen · 22 lines scan A 859626cff719
ab-harness is a plugin published in the GitHub repository wan-huiyan/claude-ecosystem-hygiene (1 stars, last pushed 22d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
api-contract-testing
Verifies API contracts between services using consumer-driven contracts, schema validation, and tools like Pact. Use when testing microservices communication, preventing breaking changes, or validating OpenAPI specifications.
api-testing
HTTP API testing for TypeScript (Supertest) and Python (httpx, pytest). Test REST APIs, GraphQL, request/response validation, authentication, and error handling.
hcf
Autonomous development orchestration with parallel TDD execution.
records
Validate FHIR R4 resources, diagnose Implementation Guide projects, explain conformance issues, and generate reviewed CI quality gates.
api-contract-keeper
Keeps your API and its spec in sync: detects and fixes OpenAPI/GraphQL spec-vs-code drift, hardens endpoints with request validation, RFC 9457 error envelopes and idempotency, guards against breaking changes, and audits job-queue reliability.
harnessay
Profile your Claude Code transcripts: context budget report, skill-promotion candidates, and a skill regression test harness. Local-only, stdlib-only.