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 skills add gpsaggese/helpers --skill git.merge_conflictsgit clone --depth 1 https://github.com/gpsaggese/helpersWrote 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.
[](https://agentmods.dev/skills/gpsaggese/helpers/git.merge_conflicts)<a href="https://agentmods.dev/skills/gpsaggese/helpers/git.merge_conflicts"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/git.merge_conflicts/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.
<a href="https://agentmods.dev/skills/gpsaggese/helpers/git.merge_conflicts"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/git.merge_conflicts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00016 | $0.00922 |
| Opus 5.5 | $0.00006 | $0.00369 |
| Sonnet 5.5 | $0.00003 | $0.00184 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
git.merge_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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
- Given a repo with unresolved Git conflicts, find why each conflict happened, resolve it, verify the result, and finalize the operation
Workflow
Identify the Operation In Progress
- Check whether the repo is in a
merge,rebase, orcherry-pick. Finalizing differs by operation> ls -a .git | grep -E "MERGE_HEAD|rebase-merge|rebase-apply|CHERRY_PICK_HEAD" - Note
<SOURCE>, the branch or commit being merged, rebased, or cherry-picked, and<TARGET>, the branch with existing history (e.g.,mainfor a merge, or the branch rebased onto)
Find the Files with Conflicts
- List the files with conflicts:
> git diff --name-only --diff-filter=U
Understand the Context
- Read the PR description, if any:
> gh pr view- If no PR is open,
gh pr viewfails: skip it and use commit history
- If no PR is open,
- Read the commits on
<SOURCE>and<TARGET>that lead to the conflict, to learn the intent of each side:> git log <TARGET>..<SOURCE> > git log <SOURCE>..<TARGET>
Propose Fixes
-
For each file with conflicts:
- List every conflict hunk (a file can have several
<<<<<<</=======/>>>>>>>blocks) - For each hunk, or group of similar hunks, explain the cause and propose a fix
- List every conflict hunk (a file can have several
-
Example
1. tutorials/GitHub_Stats/Master_GitHub_analysis.py - **Issue**: Jupytext version conflict. - **Resolution**: Use <TARGET>, it's the newer version. 2. tutorials/GitHub_Stats/docker_jupyter.sh - **Issue**: <SOURCE> adds -e GITHUB_ACCESS_TOKEN to Docker env; <TARGET> removes it. - **Resolution**: Use <TARGET> (remove the line) -
If unsure, prefer the changes from
<SOURCE>over<TARGET><TARGET>'s history is already saved, but discarding<SOURCE>'s changes could lose them permanently
Ask User and Apply the Changes
- Ask the user which resolution to apply for each ambiguous case
- Edit each conflicted file to remove the markers and apply the chosen resolution
- Confirm no conflict markers remain:
> grep -rn '^<<<<<<<\|^=======\|^>>>>>>>' <RESOLVED_FILES> - Stage each resolved file:
> git add <FILE>
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 · 103 lines · 16 tokens per session scan A bcb7027c9e20
git.merge_conflicts is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 16 tokens to every session and 922 once invoked, about $0.0001 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 2026-11-06.
git.merge_conflicts compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| git.merge_conflictsgpsaggese/helpers | Skill | 158 | today | Apache-2.0 | A | 16 | Claude Code |
| agent-merge-conflict-arbiterNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 19 | Claude Code, Codex |
| git-advanced-workflowswshobson/agents | Skill | 42k | 2d ago | MIT | A | 54 | Claude Code |
| enable-check-includes-strictchromium/chromium | Skill | 25k | today | BSD-3-Clause | A | 70 | Claude Code, Codex |
| resolve-handoffomnigent-ai/omnigent | Skill | 11k | today | Apache-2.0 | A | 23 | Claude Code, Codex |
| reproduce-and-fix-issuesbacknotprop/pstack | Skill | 3.8k | yesterday | MIT | A | 48 | Claude Code, Cursor |
| cy-orquestrate-issuecompozy/compozy | Skill | 2.9k | today | MIT | A | 94 | Claude Code, Codex |