onec-selective-export

onec-selective-export is a skill for Claude Code, Codex from Muredsa/1C-Enterprise-Agent-Toolkit. It costs 70 tokens per session (465 once invoked), scanned A, original, MIT.

A skill for selectively exporting 1C:Enterprise configuration objects, such as catalogs, documents, forms, and code modules, for inspection. 1C:Enterprise is a business-application platform with its own configuration metadata and programming language.

In plain words
What is it for?
Use it to study specific 1C objects, locate BSL code, inspect dependencies, and document the files used for your conclusions.
Why use it?
It limits the exported material to what a task needs, making it easier to inspect relevant logic and dependencies without dumping the entire configuration.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: $skill-name invocation.

Part of the onec-dev-toolkit plugin — 4 skills shipped together

Good fit Use it to study specific 1C objects, locate BSL code, inspect dependencies, and document the files used for your conclusions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/muredsa/1c-enterprise-agent-toolkit/onec-selective-export
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.

Any agent
npx skills add Muredsa/1C-Enterprise-Agent-Toolkit --skill onec-selective-export
Clone the repo
git clone --depth 1 https://github.com/Muredsa/1C-Enterprise-Agent-Toolkit

Made for: Claude Code, Codex.

Or install onec-dev-toolkit, the plugin that ships this one along with the rest of its 4 skills.

Wrote 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.

agentmods badge for onec-selective-export

README.md
[![agentmods](https://agentmods.dev/badge/skills/muredsa/1c-enterprise-agent-toolkit/onec-selective-export.svg)](https://agentmods.dev/skills/muredsa/1c-enterprise-agent-toolkit/onec-selective-export)
Your own site
<a href="https://agentmods.dev/skills/muredsa/1c-enterprise-agent-toolkit/onec-selective-export"><img src="https://agentmods.dev/badge/skills/muredsa/1c-enterprise-agent-toolkit/onec-selective-export.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 465 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00070 $0.00465
Opus 5 $0.00035 $0.00233
Sonnet 5 $0.00014 $0.00093
Haiku 4.5 $0.00007 $0.00047

Measured 8d ago against content hash 10bb35194e0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

onec-selective-export 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 8d 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.

skills/onec-selective-export/SKILL.md · 36 lines

What it actually says

1C Selective Export

Minimize the exported surface. Expand it only from concrete evidence found in the first dump.

Export workflow

  1. Read references/object-selection.md.
  2. Reuse the isolated session created by $onec-dev, or create one under the same safety contract.
  3. Normalize each requested object to a full metadata name such as Catalog.Номенклатура or Document.ЗаказПокупателя.Form.ФормаДокумента.
  4. Run selective-export --session <manifest> --object <full-name> once per root object. Use repeated --object arguments or an UTF-8 --objects-file for a small batch.
  5. Inspect the exported root XML and BSL. Add a child form, command, template, or referenced common module only when the inspected files show that it is needed.
  6. Run a second selective export with only those additional names. Do not switch to a full configuration dump for convenience.
  7. Cite the exact exported files used for conclusions.

Example:

onec.py selective-export --session <manifest> \
  --object Catalog.Номенклатура \
  --object Catalog.Номенклатура.Form.ФормаЭлемента \
  --label nomenclature-task

Accuracy rules

  • Treat an object name rejected by the CLI as unresolved; do not guess a spelling repeatedly. Confirm it from a known source or ask for the exact object.
  • Do not infer all runtime dependencies from text search. Dynamic calls and metadata references can require a targeted runtime check.
  • Keep the object list and the generated export in the session manifest so the inspection is auditable.
  • Require ok: true. Inspect the reported log if a process exits with code zero but the result or diagnostics fail.
  • Return control to $onec-dev for cleanup after the task.
Files

What ships with it

2 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. 8d ago First seen · 36 lines · 70 tokens per session scan A 10bb35194e0d

Subscribe to this mod's changes

onec-selective-export is a skill published in the GitHub repository Muredsa/1C-Enterprise-Agent-Toolkit (21 stars, last pushed 26d ago), licensed MIT. It adds 70 tokens to every session and 465 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 2026-08-30.