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/contextgit 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 | $0.01281 |
| Opus 5 | $0.00000 | $0.00641 |
| Sonnet 5 | $0.00000 | $0.00256 |
| Haiku 4.5 | $0.00000 | $0.00128 |
Grade A, and why
context 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vyuh-dxkit context
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.
Hand a coding agent (or yourself) a slim, token-budgeted structural
slice for a query — the relevant symbols, where they live, what calls
them, and the module they belong to — read from the code graph at
.dxkit/reports/graph.json. The point is to navigate by graph instead
of repeated whole-file reads: the same orientation at a fraction of the
tokens. It's a navigation aid, not a substitute for reading the code
you're about to change.
Usage
vyuh-dxkit context <query> [--budget N] [--depth N] [--substring] [--json]
vyuh-dxkit context <file:line> [--budget N] [--json]
vyuh-dxkit context … is a top-level alias for
vyuh-dxkit explore context …. The argument shape selects the mode:
a path:line resolves to the location surface (below); anything
else is a keyword query.
What it returns
A budget-bounded subgraph, breadth-first from the symbols matching the query:
- Anchor — the highest-in-degree match ("if you read one thing, read this").
- Selection — relevant symbols, seeds first, then their callers / callees, grouped by module. The walk stops once the running token estimate fills the budget, so the most relevant symbols survive truncation (reported honestly as "+N more").
- Blast radius — how many distinct callers / caller files a change to the matched symbols would touch.
On no match it returns "did you mean" suggestions instead of an empty result.
Locating by file:line
vyuh-dxkit context src/payments/checkout.ts:142
Given a location, context returns the focused source chunk around
that line — roughly the enclosing symbol rather than the whole file —
plus its structural neighborhood:
- Enclosing symbol — the declaration nearest at-or-above the line, with its in/out call counts. A heuristic: graph nodes carry only a declaration line (no end line), so the symbol boundary is declaration-to-next-declaration — confirm it before editing.
- Source chunk — the actual lines, read from disk and line-numbered,
carved to
--budgetand centered on the requested line (so the line you asked about is always shown, even when the symbol is larger than the budget). AShowing lines X–Y of the N-line spannote appears when the budget truncated the window. - Module + blast radius — the community the file belongs to and how
many caller files a change would touch (suppressed as
n/afor languages whose call graph can't be resolved — never read a blank as "0 callers"). - Callers / callees — the symbols that reach this one and the ones it calls out to.
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 · 119 lines · 0 tokens per session scan A bef0a694a36e
context 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 1,281 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.
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.
setup
Initialize a new project with SDLC-compliant structure. Creates required files, configures build system, sets up CI/CD, and establishes quality tooling.
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.