Borrowing it
Nothing to install: this file belongs to ChanMeng666/archlang. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ChanMeng666/archlang/main/.claude/commands/new-element.mdgit clone --depth 1 https://github.com/ChanMeng666/archlangWrote 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/commands/chanmeng666/archlang/new-element)<a href="https://agentmods.dev/commands/chanmeng666/archlang/new-element"><img src="https://agentmods.dev/badge/commands/chanmeng666/archlang/new-element/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.
<a href="https://agentmods.dev/commands/chanmeng666/archlang/new-element"><img src="https://agentmods.dev/badge/commands/chanmeng666/archlang/new-element.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00010 | $0.00659 |
| Opus 5.5 | $0.00004 | $0.00264 |
| Sonnet 5.5 | $0.00002 | $0.00132 |
| Haiku 4.5 | $0.00001 | $0.00066 |
Grade A, and why
new-element 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 21d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a new element
Elements are added through the registry, never a switch. Dispatch (parse / resolve / render)
goes through src/elements/defs.ts.
Steps
-
Create
src/elements/<name>.tsexporting anElementDef(follow an existing module insrc/elements/as the template — e.g. a simple leaf element). Give it atransform(el, t)so aplaced component can carry it (test/transform-seam.test.tsrequires one on every built-in); flip any handed fact whent.reflected. -
Register it in
src/elements/defs.ts. Add it to the registry so parse, resolve, and render all dispatch to it automatically. Do not add aswitchbranch anywhere. -
Keep the compiler pure. No I/O, no
Date.now(), noMath.random()in the element module. Coordinates are millimetres; origin top-left, +x right, +y down. Route number formatting throughfmt()so output stays byte-stable. Errors for bad user source are returned as aDiagnosticwith a bytespanand a cataloguedE_*/W_*code insrc/error-catalog.ts(a test enforces every raised code has an entry), never thrown. -
Declare
drawCostand the range inputs.drawCost(resolved)is an upper bound on the primitivesrender()emits (src/draw-budget.ts; without it the kind is estimated atDEFAULT_DRAW_COST, wrong for anything that grows with its size);test/drawing-budget.test.tschecks estimate >= drawn.bounds()must list every point drawn andmeasures()every other coordinate or length (an opening's width, a thickness, a radius, an offset), because the resolver holds both toMODEL_RANGE_MM(E_OUT_OF_RANGE). Any loop the element runs is charged to the step budget (src/expr.ts) or capped by a constant, before it allocates. -
Add unit tests in
test/covering parse, resolve, and render for the new element. -
npm run gen:all— if the element introduces new tokens/keywords, the generated spec, grammars, GBNF, and schemas must pick them up. (Regeneration is source-driven; never hand-edit the generated artifacts — see/regen.)
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.
- 21d ago Changed · +8 lines 5b5ad044339d
- 26d ago Changed · +2 lines 04a35394233d
- 1mo ago First seen · 38 lines · 10 tokens per session scan A 5efddf6a20a1
new-element is a command published in the GitHub repository ChanMeng666/archlang (24 stars, last pushed today), licensed MIT. It adds 10 tokens to every session and 659 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
execute_parallel
Interactive workflow for isolated parallel execution across herdr panes, testing, review, and cleanup.
auto-setup
A command that analyzes a codebase and creates project context documents, including ARCHITECTURE.md and files under .autopus/project.
auto-verify
A command for checking a website's front-end user experience with Playwright, a tool that automates web browsers.
execute
Interactive workflow for workspace isolation, pane-delegated implementation, testing, review, and cleanup.
speckit.superspec.brainstorm
../../.opencode/commands/speckit.superspec.brainstorm.md.
usually
Prompt Pocket — list your high-frequency prompts and pick one to run; manage your go-to prompts with add/delete/edit/find. Generates a native slash dropdown so you can pick a saved prompt directly.