evex: Skill for Claude Code

.agents/skills/evex-agent-authoring/SKILL.md

evex-agent-authoring is a skill for Claude Code, Codex from TommyBez/evex. It costs 30 tokens per session (2,137 once invoked), scanned A, original, MIT.

A set of rules for creating, changing, or reviewing installable Eve agents in the evex repository. It points authors to the repository’s required layout, metadata, dependencies, and documentation.

In plain words
What is it for?
Use it when authoring an Eve agent under registry/, checking its package structure, or preparing its metadata and generated files.
Why use it?
It helps keep agent packages compatible with the repository’s conventions and installable in an existing Eve app.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is TommyBez/evex's own configuration. It tells Claude Code and Codex how to work on evex itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything evex configures →

Reuse

Borrowing it

Nothing to install: this file belongs to TommyBez/evex. 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/TommyBez/evex/main/.agents/skills/evex-agent-authoring/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/TommyBez/evex

Made for: Claude Code, Codex.

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.

agentmods badge for evex-agent-authoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/tommybez/evex/evex-agent-authoring/github.svg)](https://agentmods.dev/skills/tommybez/evex/evex-agent-authoring)
Your own site
<a href="https://agentmods.dev/skills/tommybez/evex/evex-agent-authoring"><img src="https://agentmods.dev/badge/skills/tommybez/evex/evex-agent-authoring/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.

agentmods 80×15 button for evex-agent-authoring

Your own site · 80×15
<a href="https://agentmods.dev/skills/tommybez/evex/evex-agent-authoring"><img src="https://agentmods.dev/badge/skills/tommybez/evex/evex-agent-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,137 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 25
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 140
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.02137
Opus 5 $0.00015 $0.01069
Sonnet 5 $0.00006 $0.00427
Haiku 4.5 $0.00003 $0.00214

Measured 12d ago against content hash c49aae5b95cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

evex-agent-authoring 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 12d 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.

.agents/skills/evex-agent-authoring/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evex Agent Authoring

This skill carries evex repository standards only. It never restates:

  • Eve framework semantics — agent layout, tools, connections, channels, schedules, skills, evals. Read the docs shipped with the installed eve package (registry/<slug>/node_modules/eve/docs/, present after pnpm registry:install) and mirror a reference agent: list the current catalog (ls registry/) and pick the agent whose surface overlaps most — channels, connections, credentials, schedules, evals. Agents come and go, so choose from what is there now, never from memory.
  • The registry contract — package layout, registry.json field rules, dependency/author sync, eve version pinning, slug policy, generated output. CONTRIBUTIONS.md at the repo root is canonical and matches what the generator enforces; consult it instead of memory.

Ground rules for every branch:

  • Agents install into an existing Eve app via npx shadcn@latest add @evex/<slug>. Never scaffold a standalone app or publish app-level project files.
  • Canonical metadata and installable files are source-owned under registry/<slug>/; the runtime database is never the source of truth.
  • registry/ is its own pnpm workspace with its own lockfile. Run pnpm registry:install from the repo root before agent-local commands, and run agent scripts as `pnpm --dir registry --filter run
  • Keep generated output (.eve/, .output/, dist/, node_modules/) and real credentials out of the PR. Preserve unrelated working-tree changes.

Work the steps in order; each ends on a checkable bound.

1. Design

Before writing code:

  1. Read the relevant guides in the eve docs and inspect the chosen reference agent.
  2. Trace one core scenario end-to-end with realistic data: what arrives, what the agent must already know, each decision and action in order, where a human must stop the flow, what returns to the user.
  3. Derive the surface from the trace: every distinct action becomes a tool or connection, and every decision gets an owner — the model (instructions or skill), code (validation inside a tool), or a human (approval).

Read the full file on GitHub · 205 lines

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.

  1. 12d ago First seen · 205 lines · 30 tokens per session scan A c49aae5b95cb

Subscribe to this mod's changes

evex-agent-authoring is a skill published in the GitHub repository TommyBez/evex (24 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 2,137 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens