What is be-my-witness?

A screenshot review process that checks whether a user-interface image matches an automated test result and a design mockup. It combines measurable checks with a written explanation of visible differences.

Reviewing screenshots from tests or design checks, finding visual defects, and ranking those findings by severity. It can provide a pass or fail result for the review gate.

It helps distinguish real layout problems from harmless differences such as changed data or cropping. It also avoids treating a visual judgment alone as the final release decision.

be-my-witness — Skill for Claude Code by fledgeling-co

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/fledgeling-co/fledgeling-plugins

agentmods

npx agentmods add skills/fledgeling-co/fledgeling-plugins/be-my-witness

Made for: Claude Code.

Or install be-my-witness, the plugin that ships this one along with the rest of its 1 skill.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/be-my-witness/github.svg)](https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/be-my-witness)

Your own site

<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/be-my-witness"><img src="https://agentmods.dev/badge/skills/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/be-my-witness"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/be-my-witness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,202 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.

Model	Per session	Once invoked
Fable 5.1	$0.00155	$0.04202
Opus 5	$0.00077	$0.02101
Sonnet 5	$0.00031	$0.00840
Haiku 4.5	$0.00015	$0.00420

Measured 3d ago against content hash 32c06ac18b50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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 3d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (evals/run-evals.sh, evals/run-panel.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/be-my-witness/skills/be-my-witness/SKILL.md · 311 lines

How it starts

The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Be my witness

A screenshot is testimony about what the software did. This skill examines it, says what it actually shows, and refuses to take orders from it.

A screenshot arrives with a question attached: is this right? Answering it badly is easy in two opposite directions. Pixel-compare it and every honest difference — different data, a different crop, one more row in a list — reports as a failure until nobody reads the output. Ask a model "does this look right?" and it says yes, because a full-page thumbnail at 400px wide has no resolvable defects in it.

This skill does neither. It measures what can be measured, looks at what has to be looked at, and is explicit about which of three artifacts it believes.

One sentence governs the rest: the model is a localised visual critic and an explanation layer, never the release oracle. Deterministic checks decide the gate; the looking says what changed and where.

Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. Turns the verdict's coverage, bias-control and settle fields into numbers that carry the command that set them, and reads each script by its return shape rather than its exit code — checks over $? on prescan, and diffBox/diffBoxDensity over aboveRatio on diffmask, whose whole-frame ratio stays False for a localised change. Other models skip it.

The three artifacts, and which one wins

Almost every visual check involves up to three things, and conflating them is the root of most bad verdicts.

Artifact	What it is	Authority
The screenshot	What the software actually rendered	The subject. Never the arbiter.
The expected output	What the functional test asserts should happen	Behavioral Oracle. Governs data, business logic, state machines, and API interactions.
The design mock	What the design specifies for layout, typography, and controls	Visual Oracle. Governs spatial layout, text alignment, typography ramp, control hierarchy, padding, and iconography.

Read the full file on GitHub · 311 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

3d ago Changed 32c06ac18b50
11d ago First seen · 311 lines · 155 tokens per session scan A 322b9a691d23

Subscribe to this mod's changes

be-my-witness is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 155 tokens to every session and 4,202 once invoked, about $0.0008 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.

Design and UX Testing

qa-test-planner

Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.

davila7/claude-code-templates · 34 tokens

design-qa

Internal prototype QA helper. Use only after a Product Design prototype, URL-to-code build, or image-to-code build has a source visual target and a rendered implementation to compare before handoff. Do not use for broad UX critique, design critique, product audits, or flow reviews; route those user-facing requests to…

XiaomiMiMo/MiMo-Code · 68 tokens

health

Runs a budget-aware agent-assisted engineering health audit for instruction/config drift, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask in any language to audit Claude, Codex, Pi, agent instructions, MCP or hooks, verifier coverage, or AI-maintainability drift. Not for debugging application…

tw93/Waza · 71 tokens

hunt

Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects. Use when users report in any language errors, crashes, broken behavior, regressions, failing tests, screenshot evidence, or something that used to work and now fails. Not for code…

tw93/Waza · 70 tokens

chrome-cdp

Drive a headless Chrome over the Chrome DevTools Protocol (CDP) for browser QA — navigate, click, fill forms, read the DOM/accessibility tree, screenshot, and assert. Use whenever a task requires loading a web page and interacting with it like a user. Chrome is launched by a bash step (recipe below); this skill…

mattzcarey/shippie · 91 tokens

ui-craft-checks

Use this comprehensive gate for formal review, QA, launch handoff, exact-fidelity inspection, high-risk complex UI, or when the fast gate exposes a deeper craft problem. Ordinary single-screen work uses ui-design-executor and its bundled validator without loading this full matrix. Pair standalone artifacts with…

Orkas-AI/Orkas · 5 tokens