A skill for editing MAIAS documents, which describe screens, navigation, and user flows in a structured format. It keeps links between those parts correct when the document changes.

Use it to rename screens, add or remove screens and flows, change navigation, or edit screen elements while validating and formatting the result.

It avoids broken references and inconsistent documents when screens, elements, flows, or navigation are renamed or reorganized.

How MAIAS-project/maias configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to MAIAS-project/maias. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/MAIAS-project/maias/main/.claude/skills/maias-edit/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/MAIAS-project/maias

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/maias-project/maias/maias-edit/github.svg)](https://agentmods.dev/skills/maias-project/maias/maias-edit)

Your own site

<a href="https://agentmods.dev/skills/maias-project/maias/maias-edit"><img src="https://agentmods.dev/badge/skills/maias-project/maias/maias-edit/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/maias-project/maias/maias-edit"><img src="https://agentmods.dev/badge/skills/maias-project/maias/maias-edit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 858 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.

Model	Per session	Once invoked
Fable 5.1	$0.00059	$0.00858
Opus 5	$0.00030	$0.00429
Sonnet 5	$0.00012	$0.00172
Haiku 4.5	$0.00006	$0.00086

Measured 10d ago against content hash b18776d6de09, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

maias-edit 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 10d 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.

.claude/skills/maias-edit/SKILL.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

maias-edit

Apply natural-language modifications to a MAIAS document without breaking references.

Ground rules

Read docs/spec/llms.txt if you haven't this session — shapes, naming rules, canonical form.
Use the toolchain, not hand-rolled bookkeeping (./node_modules/.bin/maias; build with npm run build (repo root) if missing):
- Renames: always maias rename <file> <old_id> <new_id>. It cascades to flows, the navigation registry, and every target, then writes canonical form. Never rename by find-and-replace.
- Element changes (add/update/remove/reorder elements on a screen): use the maias MCP server's edit_elements tool when it is connected. It applies the batch atomically, refuses dangling targets and stale indices (pass expect: {type, label} as the guard), and re-validates + writes canonical form. Without the MCP server, direct-edit remains acceptable — follow the validate + fmt steps below. (Connecting it: claude mcp add maias -- node <repo>/packages/mcp/dist/cli.js after building — see packages/mcp/README.md.)
- Other edits (add/remove screens, change flows/navigation): edit the YAML directly, following the document's existing shape.
The IA is the source of truth — change the document first; renderers derive from it (see CLAUDE.md).

Process

Read the target document; locate the constructs to change (screen ids, flows, registry lists). For structural edits (screens, flows, navigation — not label/element tweaks), run maias tree <file> first and keep the output: it is your before-picture.
Apply the edit:
- Rename → maias rename (see above). If the URL path should follow the new name, update the screen's path too — the validator has no opinion, but stale paths confuse humans.
- Add screen → write the screen object, add its id to secondary.screens (or primary.screens if it's a tab), add it to the right flow, and link to it from at least one reachable screen — otherwise it will be flagged unreachable.
- Remove screen → delete the screen, its registry entry, its flow entries, and every navigation item/element target pointing at it. The validator's MAIAS-E003 will list any you miss.
Verify: maias validate <file> must report zero errors and no new warnings versus before your edit.
Canonicalise: maias fmt <file> --write.
Report what changed: ids touched, references updated, validation result. After structural edits, show maias tree <file> again so the user sees the new shape, not just a change list.

Read the full file on GitHub · 38 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.

10d ago First seen · 38 lines · 59 tokens per session scan A b18776d6de09

Subscribe to this mod's changes

maias-edit is a skill published in the GitHub repository MAIAS-project/maias (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 858 once invoked, about $0.0003 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.

Design and UX

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

maias: Skill for Claude Code