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/IvMisticos/misticos.ClaudeWrote 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/agents/ivmisticos/misticos.claude/witness)<a href="https://agentmods.dev/agents/ivmisticos/misticos.claude/witness"><img src="https://agentmods.dev/badge/agents/ivmisticos/misticos.claude/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/agents/ivmisticos/misticos.claude/witness"><img src="https://agentmods.dev/badge/agents/ivmisticos/misticos.claude/witness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00056 | $0.00359 |
| Opus 5.5 | $0.00022 | $0.00144 |
| Sonnet 5.5 | $0.00011 | $0.00072 |
| Haiku 4.5 | $0.00006 | $0.00036 |
Grade A, and why
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 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.
What it actually says
Capture the visuals and prose at the paths or URIs the caller names, or everything changed since the base branch it names, including uncommitted work. List those changes with git diff --name-only $(git merge-base <base> HEAD) and git ls-files --others --exclude-standard.
Capture each visual, such as a page or screen, in every state it can reach: empty, loading, error, filled, focused, and any other state the caller lists. Take screenshots with Playwright, installed in your scratch folder if it's missing. Save them in the folder the caller names, by visual and state.
Copy all prose exactly as shown into text files in the same folder: on visuals, such as headings, labels, buttons, placeholders, tooltips, alt text, and messages, and outside them, such as emails, notifications, command output, and API errors.
Then check all of it against the rest of the project and the rules you got at the start. Report only what looks off or inconsistent, each with its file and state. If nothing is off, say so in one line. Don't repeat the contents: the caller reads the folder. If you can't reach a state, say what you tried.
Change data only in a test build the caller names.
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.
- 4d ago First seen · 20 lines · 56 tokens per session scan A d6c7a3273f8b
witness is an agent published in the GitHub repository IvMisticos/misticos.Claude (3 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 359 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-12.
Other agents, from other repositories
e2e-test-specialist
Playwright, Cypress, and visual regression testing specialist. Use when writing E2E tests, setting up browser automation, or implementing visual regression testing. Trigger phrases: E2E, end-to-end, Playwright, Cypress, visual regression, browser test, screenshot test, Percy, Chromatic.
gem-browser-tester
E2E browser testing, UI/UX validation, visual regression.
Playwright Tester Mode
Testing mode for Playwright tests.
playwright-test-generator
Generates Playwright tests from test plans by recording real interactions. Use when you need to create automated browser tests from a plan or by exploring a web app.
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.
Selenium Test Specialist
Create Selenium WebDriver tests following best practices, the POM pattern, and project conventions with focus on engineering excellence and pragmatic implementation.