claude-jev: Instructions file for Claude Code

AGENTS.md

claude-jev AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from 0x7067/claude-jev. It costs 3,397 tokens per session, scanned A, original, MIT.

Project instructions for developing the claude-jev Claude Code plugin. They describe its files, hooks, design goals, and rules for changing the code.

In plain words
What is it for?
Use them when implementing features, reviewing changes, or maintaining the plugin's scripts, hooks, documentation, and conventions.
Why use it?
They give contributors a shared reference for how the plugin works and what it should or should not become. This reduces accidental changes to its interfaces and behavior.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: PostToolUse hook event, but also the file is AGENTS.md. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions CLAUDE.md.

This is 0x7067/claude-jev's own configuration. It tells Claude Code, Codex and OpenCode how to work on claude-jev 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 claude-jev configures →

Reuse

Borrowing it

Nothing to install: this file belongs to 0x7067/claude-jev. 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/0x7067/claude-jev/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/0x7067/claude-jev

Made for: Claude Code, Codex, OpenCode.

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 claude-jev AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/0x7067/claude-jev/agents-md/github.svg)](https://agentmods.dev/instructions/0x7067/claude-jev/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/0x7067/claude-jev/agents-md"><img src="https://agentmods.dev/badge/instructions/0x7067/claude-jev/agents-md/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 claude-jev AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/0x7067/claude-jev/agents-md"><img src="https://agentmods.dev/badge/instructions/0x7067/claude-jev/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,397 This file is loaded in full into every session.
When invoked 3,397 The same file — it is already loaded in full.
Security scan A 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03397 $0.03397
Opus 5.5 $0.01359 $0.01359
Sonnet 5.5 $0.00679 $0.00679
Haiku 4.5 $0.00340 $0.00340

Measured 2d ago against content hash d71122437654, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-30, from the pricing page.

Security

Grade A, and why

claude-jev AGENTS.md scanned grade A 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`urllib.request` is the HTTP client.
AGENTS.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

claude-jev

A Claude Code plugin. Five hooks send small judgments to TypeSafe's Jev, a System One model that returns typed answers instead of text. README.md explains what each hook decides and why. Read it before changing behavior.

Vision

VISION.md is the acceptance policy for what this plugin becomes and refuses to become. Check a non-trivial change against its align/resist pair before building it, and cite it when resisting.

Layout

Path What lives there
scripts/jev.py API client and CLI. Every other script imports it.
scripts/prompt_router.py Measurement reference for the routing eval; production runs src/prompt-router.ts under node type stripping
scripts/rules.py PostToolUse on edits, PreToolUse/PostToolUse on Bash to record shell writes, and Stop — rule enforcement
hooks/register.ts Experimental function-hooks module: session.compact -> node --experimental-strip-types src/compactor.ts rows, and the /claude-jev settings pane. A bridge, not a second implementation.
src/ The TypeScript hook implementations the plugin runs, executed directly as source under node type stripping (needs node >= 22.18)
adapters/afk/ The AFK host adapter: a TypeScript implementation of the same hooks with its own manifest, hooks.json, and README. Its known-gaps list is the contract — do not claim parity that table does not state.
scripts/comparators.py ast-grep lookups the rule hook adds to a judgment
scripts/observed.py Scores what a past turn actually did
scripts/stats.py The Stats row in /claude-jev, or python3 scripts/stats.py — scores live decisions from the three logs under ~/.claude: jev-router-log.jsonl (router, subagent, rules), jev-compact-log.jsonl, jev-calls.jsonl (every API call, written by jev.ask)
scripts/check_no_comments.py Hard ban: fails if scripts/, eval/, or hooks/ source has a # / // / /* */ comment
eval/ Offline measurement. See eval/README.md.
.claude/skills/ Maintainer skills for this repository, not shipped. release cuts a version: changelog section to bump, tag, push, GitHub release.
hooks/hooks.json Hook registration. New hook means an entry here. modules names the function-hooks module; older Claude Code ignores the key.

Read the full file on GitHub · 243 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. 2d ago Changed · +29 lines · +416 tokens per session d71122437654
  2. 4d ago Changed · +4 lines · +67 tokens per session d801d1cc4c7d
  3. 5d ago First seen · 210 lines · 2,914 tokens per session scan A 69e3b872a4aa

Subscribe to this mod's changes

claude-jev AGENTS.md is an instructions file published in the GitHub repository 0x7067/claude-jev (19 stars, last pushed 2d ago), licensed MIT. It adds 3,397 tokens to every session, about $0.0136 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-25.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,406 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 6,985 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,009 tokens