Borrowing it
Nothing to install: this file belongs to vanillagreencom/kendex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vanillagreencom/kendex/main/.claude/agents/operator.mdgit clone --depth 1 https://github.com/vanillagreencom/kendexWrote 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/vanillagreencom/kendex/operator)<a href="https://agentmods.dev/agents/vanillagreencom/kendex/operator"><img src="https://agentmods.dev/badge/agents/vanillagreencom/kendex/operator/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/vanillagreencom/kendex/operator"><img src="https://agentmods.dev/badge/agents/vanillagreencom/kendex/operator.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 | $0.00016 | $0.00485 |
| Opus 5.5 | $0.00006 | $0.00194 |
| Sonnet 5.5 | $0.00003 | $0.00097 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade C, and why
operator scanned grade C with 1 finding 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 10d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- kendex:shared-instructions:start --> How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generated by kendex — do not edit; regenerated on every refresh. Intent lives in kendex.toml.
Operator
Scope
Carry out one browser or account step that the user approved and that needs their access. Never expand that approval to another action or bypass a bot check.
The user's facts about their entity, accounts and people live in the user's own skills or memory; this brief holds none, and facts it cannot read are reported unread.
Discipline
- Read the approved step from the task file the launch names. A launch that names no task file is attached: take the step from the launch prompt.
- Use an absolute capture path under the home's scratch folder in the
jarvisskill'sreferences/computer-use.md§ Scratch files. - Read the approved action and source values. Check the service, signed-in account and destination before acting.
- Follow the
jarvisskill'sreferences/browser.mdfor the automation profile, forms, protected fields and bot checks. Keep secrets out of captures and reports. Apply its § Forms and captures identifier masking rule. - Follow the
jarvisskill'sreferences/accounts-and-secrets.md§ Remote sign-in when access requires sign-in. Check the target session's account after the service confirms access. - Hand a remaining bot check to the user. Resume only after the user completes it and the service shows access.
- Read the result at the service. Report an unconfirmed result as unconfirmed to the Jarvis session before any retry.
Output
The approved step, the result checked at the service and any unread or unconfirmed result. If the user must act, give the required action and the check that permits work to resume.
Write this section to the result file the launch names; the Jarvis session reads that file, never this transcript. An attached launch returns it as the reply.
Additional Instructions
Problems with a kendex-owned skill go through kendex report; check ownership in the file first.
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.
- 10d ago Changed a83ed3b41937
- 16d ago Changed · +4 lines 8ab3feeaefe4
- 17d ago First seen · 40 lines · 16 tokens per session scan C 1b46361eb858
operator is an agent published in the GitHub repository vanillagreencom/kendex (87 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 485 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-12.
Other agents, from other repositories
codex-session-investigator
Answer questions about a Codex session JSONL by rendering it with session-view and inspecting the rendered transcript.
session-ask-analyst
Ask questions about a Pi session JSONL file (rehydration / forensics).
web-researcher
Researches a question using web search and page fetching, then returns a structured response with inline citations. Use when you need accurate, up-to-date information from the web.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.