update

A command that regenerates files originally created by dxkit, such as the `.claude` directory and `CLAUDE.md`. It compares file contents with saved hashes so files you changed are preserved by default.

In plain words
What is it for?
Use it after upgrading dxkit to refresh its scaffolded files and migrate existing baselines or allowlists.
Why use it?
It lets you refresh generated project files after an update without overwriting work you have edited. It can also migrate saved finding baselines and allowlists when dxkit changes how findings are identified.

Command

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/vyuh-labs/dxkit/update
Clone the repo
git clone --depth 1 https://github.com/vyuh-labs/dxkit
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 791 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 $0.00000 $0.00791
Opus 5 $0.00000 $0.00396
Sonnet 5 $0.00000 $0.00158
Haiku 4.5 $0.00000 $0.00079

Measured 2d ago against content hash 363bd8fc598f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update 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 2d 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.

docs/commands/update.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vyuh-dxkit update

Run as: vyuh-dxkit <cmd> after npm install -g @vyuhlabs/dxkit, or npx @vyuhlabs/dxkit <cmd> for one-shot use. Examples on this page use the short form.

Re-generate the scaffolded files (.claude/, CLAUDE.md, etc.) while preserving files you've evolved since the original init.

Usage

vyuh-dxkit update [options]

What it does

  • Reads the manifest of files dxkit originally generated (from .vyuh-dxkit.json)
  • For each, compares the current content's hash to the at-generation hash
  • Files with unchanged hash → safe to re-generate
  • Files with changed hash → marked "evolved", preserved by default
  • Migrates your baseline + allowlist if a dxkit upgrade changed the finding-identity scheme (see below) — so the upgrade is one command, not a manual re-baseline

Identity-scheme migration (run after every upgrade)

dxkit stamps each .dxkit/baselines/*.json and .dxkit/allowlist.json with the finding-identity scheme it was written under. When a new dxkit version changes that scheme, update detects the gap and migrates automatically:

  • Re-anchors your allowlist — rewrites each entry's fingerprint onto the new scheme, preserving every reviewed suppression. You don't re-review anything or copy fingerprints from reports. (Inline dxkit-allow: source comments are unaffected — they match by location.)
  • Regenerates the baseline onto the new scheme (only if one already exists — ref-based repos gain no baseline).
  • Reports what it re-anchored / left unchanged, and flags any allowlist entry whose finding no longer exists (review + prune those).

So the full upgrade is:

npm i -D @vyuhlabs/dxkit@latest
vyuh-dxkit update
git add .dxkit && git commit -m "chore(dxkit): adopt latest"

If you skip update and run vyuh-dxkit guardrail check against a pre-upgrade committed-full baseline, the guardrail stops with an explicit "run vyuh-dxkit update" message rather than reporting every existing finding as net-new. The manual equivalent is vyuh-dxkit baseline create --force plus re-adding fingerprint-based allowlist entries by hand.

Read the full file on GitHub · 85 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. 2d ago First seen · 85 lines · 0 tokens per session scan A 363bd8fc598f

Subscribe to this mod's changes

update is a command published in the GitHub repository vyuh-labs/dxkit (10 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 791 tokens. 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.