mdvs: Skill for Claude Code

.claude/skills/code-editing/SKILL.md

code-editing is a skill for Claude Code from edochi/mdvs. It costs 43 tokens per session (680 once invoked), scanned A, original, MIT.

A set of project-specific rules for writing, changing, and removing Rust code in the mdvs codebase. It covers coding style, testing, verification, and updates needed in related specifications and documentation.

In plain words
What is it for?
Use it when implementing or changing Rust features, especially changes involving types, validation, storage, search, commands, or output. It also guides testing and downstream updates.
Why use it?
It helps developers avoid introducing patterns that conflict with the existing code and prevents changes from being missed in later parts of the data pipeline.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is edochi/mdvs's own configuration. It tells Claude Code how to work on mdvs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mdvs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to edochi/mdvs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/edochi/mdvs/main/.claude/skills/code-editing/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/edochi/mdvs

Made for: Claude Code.

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 code-editing

README.md
[![agentmods](https://agentmods.dev/badge/skills/edochi/mdvs/code-editing/github.svg)](https://agentmods.dev/skills/edochi/mdvs/code-editing)
Your own site
<a href="https://agentmods.dev/skills/edochi/mdvs/code-editing"><img src="https://agentmods.dev/badge/skills/edochi/mdvs/code-editing/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for code-editing

Your own site · 80×15
<a href="https://agentmods.dev/skills/edochi/mdvs/code-editing"><img src="https://agentmods.dev/badge/skills/edochi/mdvs/code-editing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 680 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.
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 $0.00043 $0.00680
Opus 5.5 $0.00017 $0.00272
Sonnet 5.5 $0.00009 $0.00136
Haiku 4.5 $0.00004 $0.00068

Measured 10d ago against content hash 575916902931, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-editing 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 10d 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.

.claude/skills/code-editing/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Editing Conventions

Before Writing Code

  • Read the relevant existing code first. Explore patterns, naming conventions, module structure, and error handling style already in use.
  • Match the existing style — don't introduce new patterns unless discussed with the user.
  • If the change is non-trivial, plan it with the user before coding.

Writing Code

Style

  • No wildcard imports (use arrow::array::* → explicit imports)
  • Name intermediate data structures — no unnamed tuples or raw HashMaps
  • From impls for infallible type conversions; constructors when extra parameters are needed
  • Functions that don't use self should be free functions, not methods
  • anyhow::Result for error handling in commands and I/O
  • Follow the enum-based dispatch pattern (not traits) for runtime choices
  • Never silently drop data — serialize to JSON rather than storing NULL
  • Check for collisions with internal column prefix when adding new fields

Cross-cutting changes

If the change touches the type system, a violation type, a command's output, or storage format — trace through the full pipeline:

discover → schema/config → validation → storage → search → output

Verify each stage handles the change correctly.

Testing

  • Write unit tests (#[cfg(test)] mod tests) for the changed module
  • Write integration tests for user-facing behavior changes
  • Run the full test suite, not just the changed module:
cargo test --features testing-mocks
cargo clippy --all-targets --features testing-mocks
just fmt

Always run just fmt after cargo clippy (not plain cargo fmt: the rustfmt.toml options need the pinned nightly).

Updating Specs

  • Update the relevant spec in docs/spec/ if the change affects documented behavior
  • Use the spec skill for spec writing conventions

Testing Against example_kb

  • Run the affected commands against example_kb to verify the change works end-to-end
  • If the change needs a new edge case, add it to example_kb:
    • Create or modify files to exercise the new behavior
    • Update example_kb/.plan.md with the new edge case
    • Re-run mdvs update example_kb and mdvs build example_kb --force

Read the full file on GitHub · 83 lines

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. 10d ago First seen · 83 lines · 43 tokens per session scan A 575916902931

Subscribe to this mod's changes

code-editing is a skill published in the GitHub repository edochi/mdvs (27 stars, last pushed 11d ago), licensed MIT. It adds 43 tokens to every session and 680 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-05.