GitWand: Skill for Claude Code

.claude/skills/add-pattern/SKILL.md

add-pattern is a skill for Claude Code from devlint/GitWand. It costs 59 tokens per session (2,236 once invoked), scanned A, original, MIT.

A guided workflow for adding a new automatic rule to GitWand, a tool that resolves Git merge conflicts. It covers the rule from its definition through registration and tests.

In plain words
What is it for?
Use it when GitWand must recognize and resolve a new kind of conflict, such as a specific change pattern or file situation.
Why use it?
It prevents new conflict rules from being added incompletely or with unclear behavior. The workflow collects the conditions, result, confidence, and data-risk decisions before code is changed.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is devlint/GitWand's own configuration. It tells Claude Code how to work on GitWand 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 GitWand configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import type { ClassifyInput, ConfidenceScore, PatternPlugin } from "../types.js";.

Reuse

Borrowing it

Nothing to install: this file belongs to devlint/GitWand. 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/devlint/GitWand/main/.claude/skills/add-pattern/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/devlint/GitWand

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 add-pattern

README.md
[![agentmods](https://agentmods.dev/badge/skills/devlint/gitwand/add-pattern/github.svg)](https://agentmods.dev/skills/devlint/gitwand/add-pattern)
Your own site
<a href="https://agentmods.dev/skills/devlint/gitwand/add-pattern"><img src="https://agentmods.dev/badge/skills/devlint/gitwand/add-pattern/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 add-pattern

Your own site · 80×15
<a href="https://agentmods.dev/skills/devlint/gitwand/add-pattern"><img src="https://agentmods.dev/badge/skills/devlint/gitwand/add-pattern.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,236 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 $0.00059 $0.02236
Opus 5.5 $0.00024 $0.00894
Sonnet 5.5 $0.00012 $0.00447
Haiku 4.5 $0.00006 $0.00224

Measured 2mo ago against content hash 7155a8227bdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

add-pattern 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 2mo 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/add-pattern/SKILL.md · 282 lines

How it starts

The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: add-pattern

Guide the agent through every step needed to add a new conflict-resolution pattern from end to end, touching all four required locations in the right order.


Step 1 — Gather information before writing any code

Ask the following questions up front. Do not start editing files until you have clear answers.

  1. Name — What is the snake_case name for this pattern? (e.g. comment_only_change, empty_block_insertion)

  2. Trigger condition — In plain English, when does this pattern apply? Be precise: what must be true of oursLines, theirsLines, and optionally baseLines for the pattern to fire?

  3. Resolution strategy — What should the merged output look like when this pattern fires? (accept ours, accept theirs, union, base + additions, etc.)

  4. Confidence score — What typeClassification value (0–100) do you propose, and why? What dataRisk value (0–100, where 0 = safe)? Use the existing patterns as a reference:

    • same_change / one_side_change / delete_no_change → typeClassification 100, dataRisk 0
    • non_overlapping → typeClassification 90, dataRisk 20
    • whitespace_only / reorder_only / insertion_at_boundary → typeClassification 85–90, dataRisk 8–20
    • value_only_change → typeClassification 72–88, dataRisk 25
  5. Priority — What numeric priority should this pattern have? Lower = evaluated earlier. Current assignments:

    • 10 same_change, 20 delete_no_change, 30 one_side_change
    • 40 non_overlapping, 50 whitespace_only, 55 reorder_only
    • 57 insertion_at_boundary, 60 value_only_change, 999 complex Pick a value that places it at the right point in the evaluation chain.
  6. requires — Does the pattern need the base (diff3), work without it (diff2), or both? Use "diff3", "diff2", or "both".


Step 2 — Add the ConflictType to types.ts

packages/core/src/types.ts contains the ConflictType union. Add the new type name there before creating the pattern file — TypeScript will then flag every location that needs updating.

Read the full file on GitHub · 282 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. 2mo ago First seen · 282 lines · 59 tokens per session scan A 7155a8227bdd

Subscribe to this mod's changes

add-pattern is a skill published in the GitHub repository devlint/GitWand (194 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 2,236 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 2026-08-30.

Related

add-pattern compared with skills from other repositories

add-pattern next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
add-patterndevlint/GitWandSkill194yesterdayMITA59Claude Code
hunk-launch-videomodem-dev/hunkSkill9.8kyesterdayMITA60Claude Code, Codex
hunk-releasemodem-dev/hunkSkill9.8kyesterdayMITA38Claude Code, Codex
git-macheteVirtusLab/git-macheteSkill1.1k3d agoMITA165Claude Code, Codex
mergeRockyHong/super-bootstrapSkill3yesterdayMITA130Claude Code
toura9a4k/tourSkill54mo agoMITA167Claude Code
github-pr-workflowfurkangonel/cowranglerSkill11mo agoMITB25Claude Code, Codex