merge-resolve

A procedure for resolving Git merge, rebase, or cherry-pick conflicts one section at a time. Git conflicts happen when competing changes cannot be combined automatically; the procedure then checks for leftover conflict markers and preserved test results.

In plain words
What is it for?
Use it when Git reports conflicts, to compare both sides of each conflicting change and verify the result afterward.
Why use it?
It makes conflict resolution verifiable instead of treating a clean-looking file as proof that nothing was lost.

Skill for Claude CodeCodex

Part of the whetstone plugin — 6 skills, 1 agent shipped together

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/raisedadead/claude-code-plugins/merge-resolve
Any agent
npx skills add raisedadead/claude-code-plugins --skill merge-resolve
Clone the repo
git clone --depth 1 https://github.com/raisedadead/claude-code-plugins

Made for: Claude Code, Codex.

Or install whetstone, the plugin that ships this one along with the rest of its 6 skills, 1 agent.

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 839 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00058 $0.00839
Opus 5 $0.00029 $0.00419
Sonnet 5 $0.00012 $0.00168
Haiku 4.5 $0.00006 $0.00084

Measured 2d ago against content hash a6f29b1e31be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

merge-resolve 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/verify_clean.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/whetstone/skills/merge-resolve/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

merge-resolve — resolve, then prove it clean

Two numbers make "done" checkable: zero conflict markers left, and a test pass-count at or above the pre-conflict baseline. Resolving the hunks is the first half; the numbers are the second.

When to use

  • git merge / git rebase / git cherry-pick reports a conflict.
  • The user asks to resolve conflicts or fix a merge.

Process

  1. Capture the baseline first. Before touching any conflicted file, run the suite and record the passing-test count. That count is the floor. (When the suite cannot run pre-resolution, pass - in step 3.)

  2. Resolve hunk by hunk, per reference/resolution-heuristics.md. Read both sides' diffs and pick per hunk, so each side's intent is seen before one of them loses. Regenerate lockfiles and generated files from source.

  3. Verify:

    "${CLAUDE_PLUGIN_ROOT}"/skills/merge-resolve/scripts/verify_clean.sh <root> <baseline-count> <count-command...>
    

    It exits 1 with a diagnostic on stderr in three cases: a conflict marker (<<<<<<< , >>>>>>> , ||||||| ) remains under <root>; <count-command> prints anything but a bare integer; or that integer is below <baseline-count>. There is a fourth, silent exit — the script reads the count through a command substitution under set -euo pipefail, so a <count-command> that itself exits non-zero aborts the script at that same status with nothing on stdout and no diagnostic of its own — whatever the count command wrote to stderr still passes through, so a silent count command means a silent abort. A bare grep pipeline does exactly that on a suite that printed no N passed, which is why the count command below ends in || echo 0: the run then lands in the regression arm with a message instead of vanishing into an exit code that looks like every other failure. Pass - as the baseline to check markers only.

    verify_clean.sh . 128 sh -c 'pytest -q 2>/dev/null | grep -oE "[0-9]+ passed" | grep -oE "[0-9]+" || echo 0'
    

Read the full file on GitHub · 51 lines

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. 2d ago First seen · 51 lines · 58 tokens per session scan A a6f29b1e31be

Subscribe to this mod's changes

merge-resolve is a skill published in the GitHub repository raisedadead/claude-code-plugins (2 stars, last pushed 7d ago), licensed ISC. It adds 58 tokens to every session and 839 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens