git-resolve-conflicts

A safety procedure for resolving conflicts during Git merges, rebases, cherry-picks, or pull-request updates.

In plain words
What is it for?
It helps inspect repository state, confirm the remote base, create a backup reference, and finish an interrupted or new conflict-resolution operation.
Why use it?
It reduces the risk of overwriting unrelated work or resolving conflicts against the wrong remote branch.

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/hon454/grimoire/git-resolve-conflicts
Any agent
npx skills add hon454/grimoire --skill git-resolve-conflicts
Clone the repo
git clone --depth 1 https://github.com/hon454/grimoire

Made for: Claude Code, Codex.

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 690 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 $0.00075 $0.00690
Opus 5 $0.00037 $0.00345
Sonnet 5 $0.00015 $0.00138
Haiku 4.5 $0.00007 $0.00069

Measured 2d ago against content hash 6e1ad8b69ee7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/git_conflict_preflight.py), 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/grimoire/skills/git-resolve-conflicts/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Resolve Conflicts

Use this as a safety protocol for risky Git conflict resolution. Do not use it as a general guide to interpreting code conflicts.

Required Protocol

  1. Collect Git state with the bundled read-only script. Treat it as the deterministic source for conflict-state collection.

    <python> <skill-dir>/scripts/git_conflict_preflight.py --repo .
    
  2. Stop if unrelated dirty worktree files, staged changes, or untracked files make conflict resolution ambiguous. Ask before stashing, committing, discarding, or moving them.

  3. Confirm the remote base by fetching and resolving the fetched ref:

    git fetch --prune <remote>
    git rev-parse --verify <remote>/<base>
    <python> <skill-dir>/scripts/git_conflict_preflight.py --repo . --base-ref <remote>/<base>
    
  4. Before starting a new merge or rebase attempt, create a backup ref:

    git branch backup/conflict-resolution/<branch-name> HEAD
    
  5. If a Git operation is already in progress, continue that operation. Otherwise use the user-requested operation; when unspecified, prefer rebasing onto the fetched remote base:

    git rebase <remote>/<base>
    
  6. When conflicts occur, rerun preflight before editing. Use standard Git inspection commands only as needed for path-level detail.

  7. Before asking about or resolving any non-mechanical conflict, read references/interview-gate.md.

  8. Treat semantic, product, API, data, security, ownership, and deletion-retention conflicts as mandatory stop conditions. Interview the user before resolving them.

  9. After each resolution batch, stage resolved files and continue the active operation:

    git add <paths>
    git rebase --continue
    git merge --continue
    git cherry-pick --continue
    
  10. After completion, verify with preflight, Git checks, and identifiable project checks:

<python> <skill-dir>/scripts/git_conflict_preflight.py --repo . --base-ref <remote>/<base>
git status --short --branch
git diff --check

Read the full file on GitHub · 74 lines

Files

What ships with it

3 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 · 74 lines · 75 tokens per session scan A 6e1ad8b69ee7

Subscribe to this mod's changes

git-resolve-conflicts is a skill published in the GitHub repository hon454/grimoire (2 stars, last pushed 14d ago), licensed MIT. It adds 75 tokens to every session and 690 once invoked, about $0.0004 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.