A set of instructions for an assistant that acts on a user's computer, browser, accounts, messages, or records during longer sessions. It defines which reference instructions to read before making decisions, checking results, or reporting progress.

Use it when an assistant needs to operate on the user's behalf, start or end a session, hand work to another session, request approval, or verify a result.

It provides a consistent process for handling actions, approvals, verification, and handoffs across a long session. The description does not specify particular computer or browser actions.

How vanillagreencom/kendex configures Claude Code

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/vanillagreencom/kendex/main/.agents/skills/jarvis/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/vanillagreencom/kendex

Made for: Claude Code.

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/vanillagreencom/kendex/jarvis/github.svg)](https://agentmods.dev/skills/vanillagreencom/kendex/jarvis)

Your own site

<a href="https://agentmods.dev/skills/vanillagreencom/kendex/jarvis"><img src="https://agentmods.dev/badge/skills/vanillagreencom/kendex/jarvis/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/vanillagreencom/kendex/jarvis"><img src="https://agentmods.dev/badge/skills/vanillagreencom/kendex/jarvis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,977 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. 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	$0.00033	$0.01977
Opus 5.5	$0.00013	$0.00791
Sonnet 5.5	$0.00007	$0.00395
Haiku 4.5	$0.00003	$0.00198

Measured 8d ago against content hash 632aab6b3635, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

jarvis 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 8d ago.

The scan reads SKILL.md. This mod also ships 11 executable files (scripts/lib/jarvis-env.sh, scripts/lib/op_fifo.py, scripts/lib/owner_note.py, …), 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.

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.

.agents/skills/jarvis/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Instructions

Problems with a kendex-owned skill go through kendex report; check ownership in the file first.

Jarvis

Setup

Use the home layout for the assistant home.

The declared agents, cpa, legal, operator, auditor, researcher, scout, reviewer-arch and publicist, require a kendex installation of Jarvis. Copying only the skill folder, including an app-supplied copy, supplies none of their harness agent files. Use the bundle command in README: Install from the assistant home. It installs Jarvis with its required skills, declared agents, their assigned skills and the session hooks. Installing orch alone does not install Jarvis or its declared agents.

Read the home contract when starting a session or finding a memory note.

kendex does not insert package text into AGENTS.md. The fixed persona path is persona.md, beside SKILL.md.

Plain folder

On first load, check the folder's AGENTS.md. If it lacks the persona, offer once, in one line, to add the text from persona.md. Add it only after the user agrees. The persona then loads on every turn through the harness's instruction-loading settings. Check that the harness loaded those instructions.

App-managed home

The assistant app gives persona.md to its sessions itself. A line in AGENTS.md that routes to persona.md is the persona step here. Do not offer to paste the persona text into AGENTS.md. The text would load twice.

Reachable repositories

At first load, and when the user asks which repositories Jarvis can reach, judge each folder kendex project list prints, a (worktree of [MAIN]) line by [MAIN]:

Run the folder's own .agents/skills/mailbox/scripts/lane-mail events --item overseer --box to-overseer with the folder as the working directory. Exit 0 is reachable; a mailbox nobody has written yet prints no envelope at exit 0. This probe records no read position. Read session messages through Agent reach: Read.
Anything else is unreachable. Its cause is the folder's note, a missing mailbox script, or the key lane-mail printed, such as command-missing python3 or file-unreadable.
A folder with no mailbox script but with .agents/skills/orch/ has an orch older than the mailbox package. Its cause is "refresh needed", and the offer is kendex refresh in that folder.

Read the full file on GitHub · 168 lines

Files

What ships with it

49 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.

8d ago Changed · +2 lines 632aab6b3635
10d ago Changed · +5 lines ca3062df9fba
11d ago Changed f1b7a0bbe560
13d ago Changed · +7 lines cc7be4153f70
14d ago Changed · +84 lines 6bb3f567af58
15d ago Changed · +11 lines cc26bc35f14b
16d ago Changed · +1 lines d9be30635856
17d ago Changed · +14 lines scan A → C 4892b2a16677
18d ago First seen · 44 lines · 33 tokens per session scan A 7ba74a163531

Subscribe to this mod's changes

jarvis is a skill published in the GitHub repository vanillagreencom/kendex (87 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 1,977 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 2026-10-11.

Building agents Productivity agent-management agent-manager ai-agents assistant pi-coding-agent pi-extension pi-package

prose-review

Review prose written for others (e.g., user-facing documentation, prompts for other LLMs, reports, plans, inline comments, docstrings) for local jargon leakage, orphaned references, missing grounding, and audience or genre mismatch. Always run on prose you produce or materially edit, except for routine conversational…

w-winter/dot314 · 84 tokens

kendex: Skill for Claude Code