archlang-edit-plan

archlang-edit-plan is a skill for Claude Code from ChanMeng666/archlang. It costs 102 tokens per session (932 once invoked), scanned A, original, MIT.

A workflow for editing an existing ArchLang floor-plan file. ArchLang is a file format and command-line tool for describing floor plans, and the workflow changes only the parts needed for a requested layout change.

In plain words
What is it for?
Use it to widen a room, add or move rooms and doors, or make similar changes to a .arch floor plan.
Why use it?
It helps preserve existing rooms, doors, windows, furniture, identifiers, and formatting while making a targeted change. It also checks the plan before and after editing.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the archlang plugin — 5 skills shipped together

Good fit Use it to widen a room, add or move rooms and doors, or make similar changes to a .arch floor plan.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chanmeng666/archlang/archlang-edit-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 ChanMeng666/archlang --skill archlang-edit-plan
Clone the repo
git clone --depth 1 https://github.com/ChanMeng666/archlang

Made for: Claude Code.

Or install archlang, the plugin that ships this one along with the rest of its 5 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 archlang-edit-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/chanmeng666/archlang/archlang-edit-plan/github.svg)](https://agentmods.dev/skills/chanmeng666/archlang/archlang-edit-plan)
Your own site
<a href="https://agentmods.dev/skills/chanmeng666/archlang/archlang-edit-plan"><img src="https://agentmods.dev/badge/skills/chanmeng666/archlang/archlang-edit-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 archlang-edit-plan

Your own site · 80×15
<a href="https://agentmods.dev/skills/chanmeng666/archlang/archlang-edit-plan"><img src="https://agentmods.dev/badge/skills/chanmeng666/archlang/archlang-edit-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 932 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 $0.00102 $0.00932
Opus 5.5 $0.00041 $0.00373
Sonnet 5.5 $0.00020 $0.00186
Haiku 4.5 $0.00010 $0.00093

Measured today against content hash c36bbe95aa8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

archlang-edit-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 today.

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.

plugins/archlang/skills/archlang-edit-plan/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Edit an existing plan

Change a .arch file without breaking what already works. If archlang is not on the path, write npx -y @chanmeng666/archlang in its place. Never run a bare arch: on Linux, macOS and Git Bash that name is the coreutils command.

This skill is a workflow, not a language reference. Run archlang spec for the language and archlang <cmd> --help for a command's flags.

Steps

  1. Record the starting state. Run archlang validate plan.arch --json and archlang describe plan.arch --select rooms,totals --json. Keep both results: they are what you compare against at the end. If the plan already has errors, tell the user before you edit.
  2. Read only what the change touches. archlang describe plan.arch --room <ids> --json returns those rooms with the doors, windows and furniture that touch them. archlang describe plan.arch --select freedom --json says which positions the author typed (absolute) and which the compiler derives. Change a typed number; a derived one moves by itself when the thing it depends on moves.
  3. Read the language for the forms you will write. archlang spec.
  4. Make the smallest edit. Change the statements the request names and leave the rest as they are: same ids, same order, same comments. Do not reformat the file and do not rewrite statements you were not asked to change. When a room changes size, check the walls, doors, windows and neighbouring rooms that share its edges.
  5. Compile. archlang compile plan.arch -o plan.svg --json. If ok is false, preview the mechanical fixes with archlang fix plan.arch --dry-run --json and read the diff before you apply them with archlang fix plan.arch --backup.
  6. Move furniture out of the way if needed. If the edit pushed a piece into a wall, a doorway or a door swing, archlang repair plan.arch -o plan.arch moves it. Read unresolved for the pieces it could not move.
  7. Verify the change and nothing else. Run the two commands from step 1 again. The rooms you meant to change differ as intended. Every other room has the same area and the same connections. No diagnostic is new unless the request causes it; if one is, tell the user.
  8. Refresh the sheet if the drawing grew. archlang finish plan.arch --dry-run --json shows what is missing. If it reports that the drawing no longer fits the authored paper or scale, archlang finish plan.arch --reissue may replace those two statements and nothing else.

Read the full file on GitHub · 58 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. today Changed · +1 lines · +1 tokens per session c36bbe95aa8e
  2. 4d ago First seen · 57 lines · 101 tokens per session scan A 1eceb78cccdd

Subscribe to this mod's changes

archlang-edit-plan is a skill published in the GitHub repository ChanMeng666/archlang (18 stars, last pushed today), licensed MIT. It adds 102 tokens to every session and 932 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-10.