Borrowing it
Nothing to install: this file belongs to maxbarsukov/vkr-builder. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/maxbarsukov/vkr-builder/master/.claude/skills/vkr-development/SKILL.mdgit clone --depth 1 https://github.com/maxbarsukov/vkr-builderWrote 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.
[](https://agentmods.dev/skills/maxbarsukov/vkr-builder/vkr-development)<a href="https://agentmods.dev/skills/maxbarsukov/vkr-builder/vkr-development"><img src="https://agentmods.dev/badge/skills/maxbarsukov/vkr-builder/vkr-development.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00052 | $0.00742 |
| Opus 5 | $0.00026 | $0.00371 |
| Sonnet 5 | $0.00010 | $0.00148 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
vkr-development 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 7d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on the code
src/vkr/
cli.py commands: parse, orchestrate, render the report
ui.py the only module that writes to the user
progress.py build phases as console steps
logging_setup.py logging -> findings bridge
suppress.py rule names and @suppress directives
engines.py Word / LibreOffice detection, "auto"
md.py, md_lint.py markdown parsing and checks
docx/ document building
pagination.py Word COM and LibreOffice UNO
src/tests/ pytest, run with: python -m pytest src/tests
The output rules
-
ui.pyis the only place that writes to a stream. A module that wants to tell the user something callslog.warning(...); the handler inlogging_setup.pyturns it into a finding. Neverprint(), never write tosys.stderrfrom a library module. -
Give a user-facing warning a rule so it can be suppressed and looked up:
log.warning("could not insert image %s: %s", path, exc, extra={"rule": "image"})and add that name to
suppress.RULESwith a one-line meaning — a test fails if a rule is used but not documented. -
Message style: lower-case opening, no trailing period, no module prefix (
unknown reference [рис:k], notCrossref: Unknown reference.). -
Widths are terminal columns, not code points: use
ui.text_widthandui._pad, neverlen()orljust(), for anything that lines up. A glyph the terminal draws two columns wide (any emoji) breaks every column after it — there is a test guarding the status glyphs. -
Body text keeps the terminal's own colour; colour is only for status glyphs, the title and paths, so the report reads on light and dark themes.
Commands
Each command in cli.py follows the same shape: header with context,
steps/findings, then exactly one footer (footer_ok / footer_warn /
footer_fail). Resolve the engine once through _engine(cfg, args) and put
the label in the header. Argparse never prints its own usage: -h and
errors go through this module's renderer.
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.
- 7d ago First seen · 70 lines · 52 tokens per session scan A 710cb2fdd3ef
vkr-development is a skill published in the GitHub repository maxbarsukov/vkr-builder (4 stars, last pushed 4d ago), licensed MIT. It adds 52 tokens to every session and 742 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.
Other skills, from other repositories
pos-verify
Use this immediately after files are created, edited, moved, deleted, or materially rewritten inside PersonalOS. Verifies that new truth was routed to the correct owner, written in the correct file shape, and still follows POS conventions. Do NOT use for whole-vault deep audits; use system-health-check.
kdd-accessibility-scan
Guia a cualquier agente (no depende de ningun modelo puntual) para producir un scan de accesibilidad (WCAG) de un producto en el formato de contrato de Capa 3 de KDD -- findings.json -- que despues gatea scripts/validateaccessibilityfindings.py. Usala cuando se pida auditar accesibilidad de una app/pagina, correr…
kdd-test-coverage-scan
Guia a cualquier agente (no depende de ningun modelo puntual) para producir un scan de gaps de cobertura de tests (rutas criticas sin cubrir, casos de error sin test, regresiones sin atrapar) en el formato de contrato de Capa 3 de KDD -- findings.json -- que despues gatea scripts/validatetestcoveragefindings.py. Usala…
pm-native-ccdd
Variante NATIVA del PM/orquestador CCDD que usa sub-agentes de la app de Claude (tool Agent con model override) en vez de GLM/Ollama externo. Claude autora contrato + tests congelados (oráculo), delega la IMPLEMENTACIÓN a un sub-agente barato (Haiku 4.5), y verifica por el gate CCDD determinista. Úsala cuando quieras…
delegar-pool-ccdd
Delega la IMPLEMENTACIÓN de UNA función/tarea puntual a un dev efímero vía pool exec (poolside.ai), verificada por el CCDD gate. Úsala cuando el usuario pida implementar/arreglar/extender algo puntual y quiera que lo haga pool — "delega a pool" / "usa el ccdd gate con pool". Para proyectos con VARIAS tareas y devs en…
test-personas
Internal test harness for plugin maintainers. End users should not invoke this. Runs synthetic personas through critical journeys against the plugin and produces LLM-judge findings reports. Trigger words "/test-personas", "run the test harness", "test the plugin end-to-end", "run the test personas".