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.
npx agentmods add skills/fmind/agent-levers/lever-newnpx skills add fmind/agent-levers --skill lever-newgit clone --depth 1 https://github.com/fmind/agent-leversWrote 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/skills/fmind/agent-levers/lever-new)<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>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 | $0.00040 | $0.01434 |
| Opus 5 | $0.00020 | $0.00717 |
| Sonnet 5 | $0.00008 | $0.00287 |
| Haiku 4.5 | $0.00004 | $0.00143 |
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.
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 inpackage.json). → fold into §Context implicitly.
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.
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.
- 4d ago First seen · 82 lines · 40 tokens per session scan A cfcb45439e46
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.
Other skills, from other repositories
6_gofer_validate
Validate implementation with 10-category engineering rubric (100 points).
gofer-documentation
Write or update customer-facing delivery documentation and generate its PublicAPI-capped lineage diagram. Use for Markdown, requirements, architecture, decisions, plans, validation evidence, or documentation graphs in a Gofer workspace.
eai
Start or continue the EAI delivery pipeline.
eai-update
Install or update EAI Gofer for this AI coding app.
run-agent-evolution
Run phase of an agent evolution — plan a batch of up to budget.parallel variants, dispatch sub-agents in parallel to materialize and evaluate them, learn from results, repeat until budget / wall-clock / plateau. Writes winner on a clean stop. Requires an evolution captured via /new-agent-evolution…
new-agent-evolution
Capture phase of an agent evolution — discuss the objective, gates, rubric, scope, and budget; write .agents/evolutions/ - /{evolution.yaml, EVOLUTION.md} only on explicit user agreement. Pairs with /run-agent-evolution (next) and /apply-agent-evolution (later).