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.
npx agentmods add skills/devlint/gitwand/add-patternnpx skills add devlint/GitWand --skill add-patterngit clone --depth 1 https://github.com/devlint/GitWandWhat 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 | $0.00059 | $0.02236 |
| Opus 5 | $0.00030 | $0.01118 |
| Sonnet 5 | $0.00012 | $0.00447 |
| Haiku 4.5 | $0.00006 | $0.00224 |
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 yesterday.
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 — 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.
-
Name — What is the snake_case name for this pattern? (e.g.
comment_only_change,empty_block_insertion) -
Trigger condition — In plain English, when does this pattern apply? Be precise: what must be true of
oursLines,theirsLines, and optionallybaseLinesfor the pattern to fire? -
Resolution strategy — What should the merged output look like when this pattern fires? (accept ours, accept theirs, union, base + additions, etc.)
-
Confidence score — What
typeClassificationvalue (0–100) do you propose, and why? WhatdataRiskvalue (0–100, where 0 = safe)? Use the existing patterns as a reference:same_change/one_side_change/delete_no_change→ typeClassification 100, dataRisk 0non_overlapping→ typeClassification 90, dataRisk 20whitespace_only/reorder_only/insertion_at_boundary→ typeClassification 85–90, dataRisk 8–20value_only_change→ typeClassification 72–88, dataRisk 25
-
Priority — What numeric priority should this pattern have? Lower = evaluated earlier. Current assignments:
- 10
same_change, 20delete_no_change, 30one_side_change - 40
non_overlapping, 50whitespace_only, 55reorder_only - 57
insertion_at_boundary, 60value_only_change, 999complexPick a value that places it at the right point in the evaluation chain.
- 10
-
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.
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.
- yesterday First seen · 282 lines · 59 tokens per session scan A 7155a8227bdd
add-pattern is a skill published in the GitHub repository devlint/GitWand (167 stars, last pushed 3d ago), licensed MIT. It adds 59 tokens to every session and 2,236 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.
Other skills, from other repositories
diffscope
코드 변경을 학습용 브리핑으로 바꾼다. 변경 지도 시각화 + 동작 차이 추적 + Python 문법 해설을 한 번에 터미널에 출력한다. Stop hook이 "[diffscope] 이번 턴에 소스 파일 N개가 변경되었다"라는 지시와 함께 patch 경로를 넘기면 반드시 이 스킬을 사용할 것. 사용자가 "방금 뭐 바뀐 거야", "이번 변경 설명해줘", "변경사항 설명", "이 코드 이해 안 돼", "브리핑", "다시 설명해줘", "더 자세히", "쉽게 다시", "문법만 다시", "로직만 다시", "아까 그 변경 다시 보여줘", "자동 분석 꺼줘/켜줘"라고 할 때도 이…
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
a-evolve
Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on…
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后,主动执行此流程! 将学到的经验归档为 skill,供以后参考。不要等用户提醒。.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.