v8-runner

A skill for operating `v8-runner`, a command-line tool for working with local 1C projects, including their databases, source code, builds, and tests.

In plain words
What is it for?
Use it to configure projects, create or initialize infobases and EDT workspaces, build sources, run checks and tests, convert formats, exchange artifacts, and launch 1C clients.
Why use it?
It collects the commands and safety choices needed to work with 1C projects from the terminal.

Skill for Claude CodeCodex

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 skills/alkoleft/v8-runner-rust/skill
Any agent
npx skills add alkoleft/v8-runner-rust --skill skill
Clone the repo
git clone --depth 1 https://github.com/alkoleft/v8-runner-rust

Made for: Claude Code, Codex.

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,842 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00084 $0.01842
Opus 5 $0.00042 $0.00921
Sonnet 5 $0.00017 $0.00368
Haiku 4.5 $0.00008 $0.00184

Measured 2d ago against content hash df33e294870c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

v8-runner 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.

SKILL/SKILL.md · 110 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 110 lines · 84 tokens per session scan A df33e294870c

Subscribe to this mod's changes

v8-runner is a skill published in the GitHub repository alkoleft/v8-runner-rust (57 stars, last pushed 1mo ago), licensed AGPL-3.0. It adds 84 tokens to every session and 1,842 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

odoo-mcp-real-world

Recurring end-to-end recipes for HR (employees, time off), CRM (pending responses, pipeline analysis), inventory (products with stock, warehouse moves), accounting (invoices by period), and users/groups. Use when asked to pull a report, audit, or cross-model overview rather than a single CRUD action. Triggers on…

AlanOgic/mcp-odoo-adv · 123 tokens

odoo-mcp-workflows

Trigger Odoo business actions — confirm sale orders, post invoices, validate stock pickings, mark CRM leads won/lost, convert leads to opportunities, validate timesheets. Use when a record needs a state transition beyond a simple field write (states like draft → confirmed / posted / done, cancel / reopen). Triggers on…

AlanOgic/mcp-odoo-adv · 118 tokens

odoo-mcp-batch

Execute multiple Odoo operations atomically (all succeed or all rollback) via batchexecute. Use when an operation spans multiple records or models that must be consistent — creating customer + sale order together, moving leads through stages + logging notes, or any workflow where partial success corrupts state.…

AlanOgic/mcp-odoo-adv · 104 tokens

odoo-mcp-crud

Create, update, and delete Odoo records via MCP executemethod. Use when adding new records (res.partner, crm.lead, sale.order, product.product, account.move, etc.), updating fields on existing records, bulk-updating via write, archiving, or deleting (unlink). Triggers on "create record", "add customer", "update…

AlanOgic/mcp-odoo-adv · 107 tokens

odoo-mcp-efficient-queries

Paginate, scope fields, and count-before-fetch when working with Odoo models that hold lots of data (mail.message, stock.move.line, account.move.line, sale.order.line, ir.attachment, res.partner across multi-company). Use when building a report, syncing data, iterating through all records of a model, or when a query…

AlanOgic/mcp-odoo-adv · 121 tokens

odoo-mcp-relationships

Read and write relational fields in Odoo — many2one (single link), one2many (list of child records), many2many (tag-style set). Use when creating a sale.order with order lines, tagging a partner with multiple categories, adding/removing followers, replacing a set of attributes, or when writes to relational fields fail…

AlanOgic/mcp-odoo-adv · 136 tokens