wiki-sync

A command for rebuilding pages in docs-wiki/ from their designated source documents. The wiki is a project knowledge base that connects ideas without replacing the original sources.

In plain words
What is it for?
Use it to synchronize one page, every page, or only stale pages. With no path or option, it asks which pages to update.
Why use it?
It keeps wiki pages aligned with the documents they summarize after proposals, architecture changes, or other updates. It can also limit work to pages whose source revision is out of date.

Command for Claude Code

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 commands/mendixlabs/mxcli/wiki-sync
Clone the repo
git clone --depth 1 https://github.com/mendixlabs/mxcli

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,035 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 $0.00013 $0.01035
Opus 5 $0.00006 $0.00517
Sonnet 5 $0.00003 $0.00207
Haiku 4.5 $0.00001 $0.00103

Measured yesterday against content hash 89e297ad895e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wiki-sync 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 yesterday.

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/commands/mxcli-dev/wiki-sync.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/mxcli-dev:wiki-sync — Re-synthesize Wiki Pages

Re-synthesize one or more pages in docs-wiki/ — the agent-maintained conceptual brain. The wiki frames and connects; it never re-states content that has a canonical home elsewhere.

Read .claude/skills/maintain-wiki.md first. That skill defines the page template, the synthesis rules, and the "do not duplicate" guardrails. This command is the trigger; the skill is the contract.

Arguments

  • <path> — sync a single page (e.g. architecture/mdl-execution.md).
  • --all — sync every page in docs-wiki/.
  • --stale — sync only pages whose last-synced: SHA is older than HEAD.

If invoked with no arguments, ask the user which page(s) to sync. List the seed table from maintain-wiki.md as options.

Process

Phase 1: Confirm scope

  1. Determine the page list (one path, --all, --stale, or user choice).
  2. For each page, list the current sources: from its frontmatter. Confirm with the user: "These sources will be re-read. Add or remove any?"
  3. If the user has a specific reason for the sync (a proposal landed, a refactor changed the shape of something, a new ADR), capture it in one line for the sync-log note.

Phase 2: Read sources

For each page being synced:

  1. Read every file in sources:. Do not synthesize from memory.
  2. If a source no longer exists, drop it from the list and note in the sync log.
  3. If a new source is clearly relevant (e.g. a new ADR for a rationale page), add it.

Phase 3: Re-synthesize

Follow the page template in maintain-wiki.md. For each page:

  1. Update the two body sections (What this is, How it fits) — concept- first prose, no procedure, no syntax reference, no state.
  2. Check every sentence against the "Do not duplicate" line. If a sentence belongs in a canonical home (user manual, source code, skill, ADR, proposal), cut it and link instead.
  3. Update last-synced: to git rev-parse --short HEAD.
  4. Update sources: to reflect what was actually read this run.
  5. Update the See also section with current [[wiki-link]] cross-refs.

Read the full file on GitHub · 107 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. yesterday First seen · 107 lines · 13 tokens per session scan A 89e297ad895e

Subscribe to this mod's changes

wiki-sync is a command published in the GitHub repository mendixlabs/mxcli (115 stars, last pushed 2d ago), licensed Apache-2.0. It adds 13 tokens to every session and 1,035 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.