lanes-plan

lanes-plan is a skill for Claude Code, Codex from jesseposner/metacraft. It costs 23 tokens per session (764 once invoked), scanned A, original, Apache-2.0.

A planning guide for dividing pending coding work across tmux panes, which are separate terminal workspaces that can run agents at the same time. It combines the current workspace status with the task queue to suggest assignments and order.

In plain words
What is it for?
Use it before starting parallel tasks to assign agents to features, tests, or reviews while keeping one workspace for overall coordination.
Why use it?
It makes concurrent work easier to coordinate by showing which work is available, who should handle it, and what depends on what.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it before starting parallel tasks to assign agents to features, tests, or reviews while keeping one workspace for overall coordination.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jesseposner/metacraft/lanes-plan
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.

Any agent
npx skills add jesseposner/metacraft --skill lanes-plan
Clone the repo
git clone --depth 1 https://github.com/jesseposner/metacraft

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 lanes-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/jesseposner/metacraft/lanes-plan/github.svg)](https://agentmods.dev/skills/jesseposner/metacraft/lanes-plan)
Your own site
<a href="https://agentmods.dev/skills/jesseposner/metacraft/lanes-plan"><img src="https://agentmods.dev/badge/skills/jesseposner/metacraft/lanes-plan/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 lanes-plan

Your own site · 80×15
<a href="https://agentmods.dev/skills/jesseposner/metacraft/lanes-plan"><img src="https://agentmods.dev/badge/skills/jesseposner/metacraft/lanes-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 764 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.
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 $0.00023 $0.00764
Opus 5 $0.00012 $0.00382
Sonnet 5 $0.00005 $0.00153
Haiku 4.5 $0.00002 $0.00076

Measured 9d ago against content hash 6589aedac987, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

lanes-plan 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 9d 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/lanes-plan/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lanes Plan

Read the current workspace state and the work queue, then propose how to allocate lanes.

Process

1. Get current state

Run a lanes status view first (see lanes-status). You need to know what's available before you can plan.

2. Read the work queue

Check for pending work items. Look at:

  • The project's task list, active items, or session plan
  • Any state files or roadmap docs that define what's next
  • Recent conversation context for work that's been discussed but not started

3. Propose assignments

For straightforward allocations, a per-pane list:

Pane: 0 (left)
Assignment: Meta (us)
Work: Orchestration, review, decisions
────────────────────────────────────────
Pane: 1 (upper-right)
Assignment: Coding Agent A
Work: Auth middleware + tests (item 1)
────────────────────────────────────────
Pane: 2 (lower-right)
Assignment: Coding Agent B
Work: API handlers for items 2-4

For complex layouts with dependencies, a spatial view:

┌─────────────────────────────┬─────────────────────────────┐
│                             │                             │
│   META (me)                 │   AGENT A                   │
│   Upper Left                │   Upper Right               │
│                             │                             │
│   Coordination, reviews,    │   Auth middleware + tests    │
│   architecture decisions    │   (item 1, the complex one) │
│                             │                             │
│   Always present.           │   Long-lived. Spin up now,  │
│   Light context.            │   independent, no blockers. │
│                             │                             │
├─────────────────────────────┼─────────────────────────────┤
│                             │                             │
│   AGENT B                   │   FLEX                      │
│   Lower Left                │   Lower Right               │
│                             │                             │
│   API handlers for items    │   Available for:            │
│   2-4 (same pattern)        │   - Code reviews as PRs     │
│                             │     come in                 │
│   Depends on A's middleware │   - Ad hoc investigation    │
│   landing first.            │                             │
│                             │   Spin up when needed,      │
│                             │   idle otherwise.           │
│                             │                             │
└─────────────────────────────┴─────────────────────────────┘

Read the full file on GitHub · 92 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. 9d ago First seen · 92 lines · 23 tokens per session scan A 6589aedac987

Subscribe to this mod's changes

lanes-plan is a skill published in the GitHub repository jesseposner/metacraft (11 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 764 once invoked, about $0.0001 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.