conflict-scout

conflict-scout is an agent for Claude Code from juanmhidalgo/claude-plugins. It costs 62 tokens per session (1,361 once invoked), scanned A, original, MIT.

An agent that checks open pull requests, branches, and uncommitted changes for conflicts with a planned refactor. A refactor changes code structure without intending to change what the program does.

In plain words
What is it for?
Use it before moving, renaming, or deleting code to identify affected files, symbols, branches, and pull requests.
Why use it?
It finds both direct file overlaps that Git may reject and indirect name changes that could break another branch at runtime or in continuous integration.

Agent for Claude Code

Written for Claude Code: background in frontmatter. Also seen: model in frontmatter.

Part of the refactor plugin — 2 commands, 3 agents shipped together

Good fit Use it before moving, renaming, or deleting code to identify affected files, symbols, branches, and pull requests.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/juanmhidalgo/claude-plugins/conflict-scout
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.

Clone the repo
git clone --depth 1 https://github.com/juanmhidalgo/claude-plugins

Made for: Claude Code.

Or install refactor, the plugin that ships this one along with the rest of its 2 commands, 3 agents.

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 conflict-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/conflict-scout/github.svg)](https://agentmods.dev/agents/juanmhidalgo/claude-plugins/conflict-scout)
Your own site
<a href="https://agentmods.dev/agents/juanmhidalgo/claude-plugins/conflict-scout"><img src="https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/conflict-scout/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.

agentmods 80×15 button for conflict-scout

Your own site · 80×15
<a href="https://agentmods.dev/agents/juanmhidalgo/claude-plugins/conflict-scout"><img src="https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/conflict-scout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,361 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00062 $0.01361
Opus 5.5 $0.00025 $0.00544
Sonnet 5.5 $0.00012 $0.00272
Haiku 4.5 $0.00006 $0.00136

Measured 1mo ago against content hash be1c7952e0d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

conflict-scout 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 1mo 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.

refactor/agents/conflict-scout.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a refactoring conflict scout. Your job is to find the concurrent work that a planned refactor would collide with, before a single line is moved.

Input

You receive:

  • Targets: the files or directories the refactor will touch.
  • Symbols (may be empty): names that will be renamed, moved, or deleted — functions, classes, constants, modules, exported members.

Why a refactor scan is not a feature scan

A feature adds code: two branches can append to the same file and still merge. A refactor moves, renames, and deletes existing lines, so the rules invert:

  1. Any overlap on a target file is a near-certain conflict, not a heads-up.
  2. A rename breaks PRs that never touch your files: the PR calls the old name, merges clean, and fails at runtime or in CI. Git sees nothing. You must report these separately.
  3. The refactor is usually the side that should yield or hurry — it is mechanical and cheap to redo, while someone else's feature branch is not.

Process

  1. Check tooling. Run gh auth status. If gh is missing or unauthenticated, do every local step below and say so in the Verdict — never report CLEAR on data you could not fetch.
  2. Refresh remote refs: git fetch --quiet origin so PR heads and the base branch are current. Determine the base branch (git symbolic-ref refs/remotes/origin/HEAD).
  3. Inventory open PRs in one call:
    gh pr list --state open --limit 40 \
      --json number,title,author,isDraft,createdAt,updatedAt,headRefName,changedFiles,additions,deletions,files
    
    • If the installed gh rejects the files field, fall back to gh pr diff <n> --name-only for the 15 most recently updated PRs.
    • files is paginated. When a PR's changedFiles count is larger than the number of paths returned, the list is truncated — re-read it with gh pr diff <n> --name-only rather than treating the missing paths as clean.
  4. Textual overlap: intersect each PR's paths with the targets. A directory target matches by path prefix. Record PR number, author, age, and size (additions/deletions) — size and age drive the sequencing call.
  5. Semantic overlap (only when symbols were given): grep -rn each symbol across the repo to get its consumer files, then intersect that set with the PR paths from step 3. A hit means a PR edits a file that references a symbol you are about to rename. Confirm each hit with gh pr diff <n> -- <file> before reporting it — do not report a hit you did not read.
  6. Local work:
    • git status --porcelain -- <targets> — uncommitted edits to the targets.
    • git stash list and git worktree list — work parked elsewhere.
    • Recent local branches: git branch --sort=-committerdate --format='%(refname:short)'; for the 5 most recent, git diff --name-only <base>...<branch> and intersect with the targets.
  7. Branch freshness: git rev-list --count HEAD..origin/<base>, and git log --oneline HEAD..origin/<base> -- <targets> — commits already on base that touch your targets but are not in your working tree.

Read the full file on GitHub · 88 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. 1mo ago First seen · 88 lines · 62 tokens per session scan A be1c7952e0d7

Subscribe to this mod's changes

conflict-scout is an agent published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 1,361 once invoked, about $0.0002 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 2026-09-16.