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.
npx agentmods add commands/vyuh-labs/dxkit/updategit clone --depth 1 https://github.com/vyuh-labs/dxkitWhat 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 | $0.00000 | $0.00791 |
| Opus 5 | $0.00000 | $0.00396 |
| Sonnet 5 | $0.00000 | $0.00158 |
| Haiku 4.5 | $0.00000 | $0.00079 |
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.
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>afternpm install -g @vyuhlabs/dxkit, ornpx @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
fingerprintonto the new scheme, preserving every reviewed suppression. You don't re-review anything or copy fingerprints from reports. (Inlinedxkit-allow:source comments are unaffected — they match by location.) - Regenerates the baseline onto the new scheme (only if one already
exists —
ref-basedrepos 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.
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.
- 2d ago First seen · 85 lines · 0 tokens per session scan A 363bd8fc598f
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.
Other commands, from other repositories
readme-audit
Audit a README's reading flow by treating it as a conversion funnel. Every section is evaluated against a target reader and a terminal action. Produces a structured audit blueprint that feeds directly into /readme-restructure.
setup
Initialize a new project with SDLC-compliant structure. Creates required files, configures build system, sets up CI/CD, and establishes quality tooling.
readme-restructure
Execute a /readme-audit blueprint. Rewrites the README to the evaluator → conversion → links structure and creates linked docs by extracting and reorganising existing content.
validate
Run SDLC compliance check against the current project. Validates build system, code quality, testing, CI/CD, security, documentation, VCS, and release configurations.
run-tests
Run automated functional tests using the hook-driven test framework. Execute the test suite to validate all project functionality.
test-report
Generate test execution report in markdown format.