resolve-conflicts

resolve-conflicts is a skill for Claude Code, Codex from fmind/dot. It costs 40 tokens per session (1,043 once invoked), scanned A, original, MIT.

A method for resolving Git merge or rebase conflicts by understanding what both versions of each file were intended to do.

In plain words
What is it for?
Use it to inspect conflicting commits and file versions, resolve the intended result, continue the merge or rebase, and rerun checks.
Why use it?
It prevents changes from being discarded blindly when two branches modify the same code or files.

Skill for Claude CodeCodex

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/fmind/dot/resolve-conflicts
Any agent
npx skills add fmind/dot --skill resolve-conflicts
Clone the repo
git clone --depth 1 https://github.com/fmind/dot

Made for: Claude Code, Codex.

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 resolve-conflicts

README.md
[![agentmods](https://agentmods.dev/badge/skills/fmind/dot/resolve-conflicts.svg)](https://agentmods.dev/skills/fmind/dot/resolve-conflicts)
Your own site
<a href="https://agentmods.dev/skills/fmind/dot/resolve-conflicts"><img src="https://agentmods.dev/badge/skills/fmind/dot/resolve-conflicts.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,043 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 $0.00040 $0.01043
Opus 5 $0.00020 $0.00522
Sonnet 5 $0.00008 $0.00209
Haiku 4.5 $0.00004 $0.00104

Measured yesterday against content hash b74b176bef73, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

resolve-conflicts 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.

skills/resolve-conflicts/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resolve Conflicts

Finish a stopped git merge or git rebase by understanding what each side meant, not by picking a side. Never --abort to make the problem disappear, and never "take ours" unless history shows the other change is obsolete. Branch naming lives in feature-branch; committing and pushing in git-add-commit-push.

Workflow

  1. Map the state: which operation stopped, which files conflict, and which commits touch them.
    git status --short                    # UU both modified; AU, UA, DU, UD: added or deleted on one side
    git diff --name-only --diff-filter=U
    git log --merge --oneline -- <file>   # commits from both heads that touch the file
    
  2. Read both intents: for each file, compare the working tree with the three stages and read the history behind each side (commit messages, linked pull requests and issues) before touching a hunk.
    git diff --base <file>     # against the common ancestor
    git diff --ours <file>     # against our side (rebase: the branch being rebased onto)
    git diff --theirs <file>   # against their side (rebase: the commit being replayed)
    git log -p $(git merge-base HEAD MERGE_HEAD)..MERGE_HEAD -- <file>   # rebase: REBASE_HEAD
    
  3. Resolve semantically: write the code that satisfies both intents (renamed function plus new caller, both new tests, merged config keys). When intents are incompatible, keep the one matching the merge's goal and record the trade-off in the commit body. Do not invent new behavior, and remove every <<<<<<<, =======, >>>>>>> marker.
  4. Continue: stage the resolved files and resume; repeat per commit during a rebase.
    git add <file>...
    git rebase --continue   # or: git merge --continue
    
  5. Prove it: Run the full gate (mise run all); if the tree carries unrelated changes and the gate write-formats, run it in a temporary git worktree or fall back to mise run check and mise run test (see mise). Fix what the merge broke before pushing.
  6. Push: a rebased private branch needs git push --force-with-lease; never force-push a shared branch (main, or one others build on), merge into it instead.

Read the full file on GitHub · 53 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. yesterday First seen · 53 lines · 40 tokens per session scan A b74b176bef73

Subscribe to this mod's changes

resolve-conflicts is a skill published in the GitHub repository fmind/dot (4 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,043 once invoked, about $0.0002 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 2026-09-03.