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/fledgeling-co/fledgeling-pluginsWrote 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/fledgeling-co/fledgeling-plugins/be-my-witness)<a href="https://agentmods.dev/plugins/fledgeling-co/fledgeling-plugins/be-my-witness"><img src="https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/be-my-witness/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/fledgeling-co/fledgeling-plugins/be-my-witness"><img src="https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/be-my-witness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
be-my-witness 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.
What it actually says
{
"name": "be-my-witness",
"description": "Validate a UI screenshot against what a test expected and against a design mock, returning a pass/fail gate plus severity-ranked findings. Runs a deterministic pre-scan first (is this evidence, did the surface settle, are the two framings even comparable), crops and zooms rather than judging a full-page thumbnail, looks at every pair in both orders to catch position bias, and classifies each difference as framing, data, structure, styling or state so a changed row count or a different crop cannot fail a build. The test expectation is the oracle; the mock is advisory.",
"version": "0.3.1",
"author": {
"name": "Fledgeling",
"email": "[email protected]"
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 155 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.
- 1mo ago Changed 26d3800a62a7
- 1mo ago First seen · 10 lines scan A 62647c696f50
be-my-witness is a plugin published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed yesterday), 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
accessibility-compliance
WCAG accessibility auditing, compliance validation, UI testing for screen readers, keyboard navigation, and inclusive design.
stuntdouble
Deploy AI user personas to validate user journeys at scale. Find UX friction before real users do.
muki-ai-plugins marketplace
Muki's Claude Code plugins — project lore knowledge base, test quality review, code review with sub-agent voting, visual regression testing, AI session review, Jev-powered web search, a virtual pet that grows from your Claude Code work, and world news under your prompt.
e2e
E2E test triage, debugging, and fix implementation toolkit.
meticulous
Agent skills for Meticulous visual regression testing — review test runs, investigate replays, debug diffs. Also connects the hosted Meticulous MCP server.
playwright-e2e
Author and maintain resilient Playwright end-to-end tests using the Page Object Model, fixtures, stable user-facing locators, and web-first assertions. Enforces guardrails against flakiness, brittle selectors, and shared state. Drives Playwright's built-in planner, generator, and healer agents (playwright-test MCP)…