agentmods.dev

lever-init

A setup command for an agent-levers project. It creates the folders and instruction files that coding agents use to follow the project's working rules.

In plain words
What is it for?
Use it to prepare a Git repository for agent-levers, create a missing AGENTS.md starting point, and connect Claude Code and Gemini CLI to AGENTS.md.
Why use it?
It removes the need to create those files and connect each supported coding assistant by hand. It also checks that the repository is suitable before making changes.

Skill for Claude CodeCodex

3 3mo ago A scan 48 tokens original MIT
View the source file fmind/agent-levers
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-init
Any agent
npx skills add fmind/agent-levers --skill lever-init
Clone the repo
git clone --depth 1 https://github.com/fmind/agent-levers

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,105 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 $0.00048 $0.01105
Opus 5 $0.00024 $0.00553
Sonnet 5 $0.00010 $0.00221
Haiku 4.5 $0.00005 $0.00111

Measured 2d ago against content hash 7bee15d6ef62, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lever-init 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 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.

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-init/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

lever-init

Bootstrap this repo for agent-levers. Idempotent: only adds files. The one exception is §3 — when AGENTS.md exists but doesn't reference the lever skills, init appends a Workflow section pointing at them.

GitHub Copilot reads AGENTS.md natively; Claude Code (CLAUDE.md) and Gemini CLI (GEMINI.md) need a one-line @-import shim.

1. Pre-flight

  1. Confirm the cwd is a git repo: git rev-parse --is-inside-work-tree. If not, stop with "Blocked: not a git repository — run \git init` first."`

  2. Run git status --porcelain. If non-empty, list dirty paths under a Pre-existing changes: heading in the chat reply and proceed — init only adds files.

  3. Confirm .agents/levers/ is not git-ignored (handles negations, nested .gitignores, glob patterns, portable across Linux/macOS/Windows Git Bash):

    git check-ignore -q .agents/levers/.gitkeep

    Exit 0 means the path is ignored. Surface the offending line(s) with grep -n '\.agents' .gitignore and stop with a chat sentence naming the gitignored path.

2. Workspace skeleton

mkdir -p .agents/levers

3. AGENTS.md

AGENTS.md is the project's contract with its agents — voice, conventions, layout, workflow. Three cases:

  • Missing. Write templates/AGENTS.md (sibling of this SKILL.md) verbatim. Surface in chat: "Wrote AGENTS.md from the lever-init skeleton — fill in the placeholders before running /lever-new."
  • Exists, mentions any of /lever-new, /lever, /lever-status. No-op. The workflow is already wired.
  • Exists, no lever mention. Append a Workflow section pointing at /lever-new, /lever, /lever-status (and /lever-status <id> cancel [<reason>] for retirement). Use the Workflow bullets from templates/AGENTS.md. If the file already has a ## Workflow heading, append at its end (before the next ## or EOF); otherwise add a new ## Workflow section. Surface in chat: "Appended a Workflow section to AGENTS.md — review and revert if you'd rather wire the skills differently."

Read the full file on GitHub · 75 lines

Files

What ships with it

1 file 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. 2d ago First seen · 75 lines · 48 tokens per session scan A 7bee15d6ef62

Subscribe to this mod's changes

lever-init is a skill published in the GitHub repository fmind/agent-levers (3 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 1,105 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.

Building agentsagent-skillsagentic-codingclaude-codegemini-cligithub-copilotworkflow
Related

Other skills, from other repositories

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…

fmind/agent-evolutions · 81 tokens

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).

fmind/agent-evolutions · 74 tokens

spec-kitty-implement-review

Orchestrate the implement-review loop for Spec Kitty work packages using any configured agent. Covers agent dispatch, state transitions, rejection cycles, arbiter escalation, and dependency-aware sequencing across all 13 supported coding agents. Triggers: "implement and review WPs", "run the implement-review loop"…

Priivacy-ai/spec-kitty · 120 tokens

spec-kitty-mission-system

Understand how Spec Kitty missions work: the 4 built-in mission types, how they define workflows via step contracts and action indices, how missions and work packages relate, how templates are resolved through the 6-tier chain, and how doctrine artifacts (procedures, tactics, directives) compose mission behavior.…

Priivacy-ai/spec-kitty · 160 tokens

spec-kitty-orchestrator-api-operator

Teach agents and external systems how to use spec-kitty orchestrator-api to drive workflows from outside the host CLI. Triggers: "use orchestrator-api", "build a custom orchestrator", "automate externally", "integrate CI with spec-kitty", "call spec-kitty from another tool", "orchestrator contract", "external…

Priivacy-ai/spec-kitty · 125 tokens

spk-doctrine-profile-load

Load a Spec Kitty agent profile on demand for interactive sessions, including identity, governance scope, boundaries, and initialization.

Priivacy-ai/spec-kitty · 30 tokens