lever-new

lever-new is a skill for Claude Code, Codex from fmind/agent-levers. It costs 40 tokens per session (1,434 once invoked), scanned A, original, MIT.

A command for starting a new lever, where a lever is a tracked piece of coding work with a defined goal and workflow.

In plain words
What is it for?
Use it to discuss an ask, record the goal, success criteria, context, and open questions, then create the lever after the user agrees.
Why use it?
It helps turn a loosely described request into a shared written brief before implementation begins, reducing misunderstandings and repeated questions later.

Skill for Claude CodeCodex

Part of the agent-levers plugin — 4 skills shipped together

Install

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.

agentmods
npx agentmods add skills/fmind/agent-levers/lever-new
Any agent
npx skills add fmind/agent-levers --skill lever-new
Clone the repo
git clone --depth 1 https://github.com/fmind/agent-levers

Made for: Claude Code, Codex.

Or install agent-levers, the plugin that ships this one along with the rest of its 4 skills.

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 lever-new

README.md
[![agentmods](https://agentmods.dev/badge/skills/fmind/agent-levers/lever-new.svg)](https://agentmods.dev/skills/fmind/agent-levers/lever-new)
Your own site
<a href="https://agentmods.dev/skills/fmind/agent-levers/lever-new"><img src="https://agentmods.dev/badge/skills/fmind/agent-levers/lever-new.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,434 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00040 $0.01434
Opus 5 $0.00020 $0.00717
Sonnet 5 $0.00008 $0.00287
Haiku 4.5 $0.00004 $0.00143

Measured 4d ago against content hash cfcb45439e46, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lever-new 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.

skills/lever-new/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

lever-new

Capture user intent — what to build, what success looks like — as the lever's inaugural §Brief. The brief is a contract about WHAT to build; the chain that follows (/lever <id> → plan → do → check → act) owns mechanism, work, and verification.

§Brief is the input to the chain. The chain reads it, investigates, builds the spec, executes, and verifies. The chat session before the brief lands is the human's last guaranteed touchpoint with the lever — capture enough that the chain can run end-to-end without pausing to re-ask.

Dialog first (hard rule). First-turn output is chat-only: clarifying questions, proposed enhancements, and a draft brief inline. Do not create .agents/levers/<id>-<slug>/, do not write LEVER.md, do not seed lever.yaml until the user explicitly agrees (typed acknowledgment, "looks good", edits incorporated). Files commit on the second turn at earliest. Brief is the cheapest place to improve intent.

1. Pre-flight (read-only)

First-turn pre-flight is reads only — no file writes, no directory creation. Read in order: AGENTS.md (and any nested ones), README.md, the user ask, any spec the ask points at (e.g., TASK.md, design doc, link).

Goal: know enough to ask sharp questions and sketch a draft. Stop when you can classify §2's ambiguities and propose a draft.

2. Discuss and propose

For each ambiguity, classify:

  • User-only — irreducible, only the user can answer (business rules, scope boundaries, irreversible architectural choices, security posture, deadlines, new third-party dependencies). → escalate as a clarifying question in chat.
  • Investigation-resolvable — the chain can answer it by reading the codebase or external docs (which file owns this, which test framework is wired, what the existing pattern looks like). → note for §Open questions; the chain resolves these without coming back.
  • Conventional default — project context already dictates an answer (a rule in AGENTS.md §Conventions, a preset in package.json). → fold into §Context implicitly.

Read the full file on GitHub · 82 lines

Files

What ships with it

2 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.

  1. 4d ago First seen · 82 lines · 40 tokens per session scan A cfcb45439e46

Subscribe to this mod's changes

lever-new is a skill published in the GitHub repository fmind/agent-levers (3 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 1,434 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 2026-08-31.