merge-resolver

merge-resolver is an agent for coding agents from Effulgent-Point/paw. It costs 26 tokens per session (377 once invoked), scanned A, original, MIT.

An agent that resolves Git merge conflicts by comparing the changes on both sides and combining compatible work. A merge conflict happens when Git cannot safely decide how overlapping edits should fit together.

In plain words
What is it for?
Use it to inspect conflicted files, resolve compatible changes, identify competing decisions for review, run related tests, and stage resolved files.
Why use it?
It prevents blindly choosing one version and preserves both intentions when the edits can coexist.

Agent

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 agents/effulgent-point/paw/merge-resolver
Clone the repo
git clone --depth 1 https://github.com/Effulgent-Point/paw

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 merge-resolver

README.md
[![agentmods](https://agentmods.dev/badge/agents/effulgent-point/paw/merge-resolver.svg)](https://agentmods.dev/agents/effulgent-point/paw/merge-resolver)
Your own site
<a href="https://agentmods.dev/agents/effulgent-point/paw/merge-resolver"><img src="https://agentmods.dev/badge/agents/effulgent-point/paw/merge-resolver.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 377 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 $0.00026 $0.00377
Opus 5 $0.00013 $0.00188
Sonnet 5 $0.00005 $0.00075
Haiku 4.5 $0.00003 $0.00038

Measured 4d ago against content hash fdf11acb8141, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

merge-resolver 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 4d ago.

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.

agents/merge-resolver.md · 53 lines

What it actually says

Role

Resolve merge conflicts intelligently. Read both sides of each conflict, understand what each was trying to do, and produce a resolution that preserves both intents.

Context

Load contexts/dev.md.

Skill

Load skills/git-safety/SKILL.md.

Rules

  • rules/git-doctrine.md — merge, never rebase
  • rules/test-first.md — run tests after resolution

Process

  1. Run git diff --name-only --diff-filter=U to list conflicted files.
  2. For each conflicted file, read the full file with conflict markers.
  3. For each conflict hunk:
    • Identify what the "ours" side was trying to do.
    • Identify what the "theirs" side was trying to do.
    • If compatible (both adding different things): combine both.
    • If competing (both changing the same logic differently): escalate to user.
  4. Write the resolved file.
  5. Run related tests to verify the resolution.
  6. git add each resolved file.

Failure modes

  • Can't determine intent → escalate to user with both sides annotated
  • Tests fail after resolution → do not commit, show failing tests
  • More than 5 conflicted files → flag for user review before resolving

What NOT to do

  • Do not blindly pick "ours" or "theirs".
  • Do not resolve conflicts you don't understand.
  • Do not commit the merge — leave that to the user.

Done when

All conflict markers removed, both sides' intent preserved, tests pass.

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. 4d ago First seen · 53 lines · 26 tokens per session scan A fdf11acb8141

Subscribe to this mod's changes

merge-resolver is an agent published in the GitHub repository Effulgent-Point/paw (2 stars, last pushed 24d ago), licensed MIT. It adds 26 tokens to every session and 377 once invoked, about $0.0001 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.