resolve-single-comment

resolve-single-comment is a command for GitHub Copilot from microsoft/copilot-for-eclipse. It costs 9 tokens per session (1,424 once invoked), scanned A, original, MIT.

A gated procedure for resolving one pull-request review comment. It tells the agent how to inspect the comment's file and context and requires user approval at specified steps.

In plain words
What is it for?
Use it to investigate and resolve a single comment on a GitHub pull request.
Why use it?
It prevents an agent from changing code or completing a review response without understanding the request and receiving the required confirmation.

Command for GitHub Copilot ✓ vendor

Written for GitHub Copilot: a Copilot chat mode or prompt. Also seen: agent in frontmatter.

Good fit Use it to investigate and resolve a single comment on a GitHub pull request.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/microsoft/copilot-for-eclipse/resolve-single-comment
About the project

GitHub Copilot for Eclipse is an Eclipse IDE plugin that adds AI-assisted code completion, edit suggestions, conversational agent support, and connections to external tools through MCP. Eclipse developers use it for coding assistance and more autonomous, project-aware development tasks. The catalogue entries provide skills and instructions for working with Copilot in Eclipse.

microsoft/copilot-for-eclipse · 122 stars · on GitHub · marketplace.eclipse.org

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/microsoft/copilot-for-eclipse

Made for: GitHub Copilot.

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-single-comment

README.md
[![agentmods](https://agentmods.dev/badge/commands/microsoft/copilot-for-eclipse/resolve-single-comment.svg)](https://agentmods.dev/commands/microsoft/copilot-for-eclipse/resolve-single-comment)
Your own site
<a href="https://agentmods.dev/commands/microsoft/copilot-for-eclipse/resolve-single-comment"><img src="https://agentmods.dev/badge/commands/microsoft/copilot-for-eclipse/resolve-single-comment.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,424 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 $0.00009 $0.01424
Opus 5 $0.00005 $0.00712
Sonnet 5 $0.00002 $0.00285
Haiku 4.5 $0.00001 $0.00142

Measured yesterday against content hash f34698e15a39, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

resolve-single-comment 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.

.github/prompts/resolve-single-comment.prompt.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Single PR Comment Resolution

When to Apply

Apply this instruction when resolving an individual PR review comment. This is typically invoked as part of the broader PR comment resolution workflow.

Critical Rules

⚠️ THIS IS A BLOCKING WORKFLOW: Each step must complete before proceeding to the next.

CONFIRMATION STEPS ARE MANDATORY: Steps 4 and 8 require explicit user approval. You MUST stop and wait for user input.

DO NOT PROCEED WITHOUT CONFIRMATION: If the user has not responded, DO NOT continue to the next step.

Input

  • pr_number: The PR number
  • comment_id: The comment ID from the comments.json file

Read the comment details from .github/pullrequests/{pr_number}/comments.json using the comment_id:

  • id: The comment ID (for replying)
  • path: The file path where the comment was made
  • line: The line number in the file
  • body: The review comment content

Resolution Steps

1. Understand the Context

  1. Read the file at the specified line and surrounding context (±10-20 lines)
  2. Parse the comment body to understand what the reviewer is requesting
  3. If more context is needed, read additional lines from the file

2. Classify the Comment Type

Determine the type of feedback:

  • Code style: Formatting, naming conventions, import organization
  • Bug fix: Logic error, null check, edge case handling
  • Refactoring: Extract method, simplify logic, reduce duplication
  • Documentation: Add/update Javadoc, comments, or explanations
  • Best practice: Thread safety, resource management, error handling
  • Question/Clarification: Reviewer needs explanation (may not require code change)

3. Propose the Fix

  1. Identify the specific change needed
  2. Present the proposed change to the user with:
    • What will be changed
    • Why this addresses the reviewer's feedback
    • Any related changes needed (e.g., updating callers)

4. Get User Confirmation ⛔ BLOCKING STEP

⛔ STOP HERE AND WAIT FOR USER RESPONSE

Read the full file on GitHub · 161 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 · 161 lines · 9 tokens per session scan A f34698e15a39

Subscribe to this mod's changes

resolve-single-comment is a command published in the GitHub repository microsoft/copilot-for-eclipse (122 stars, last pushed yesterday), licensed MIT. It adds 9 tokens to every session and 1,424 once invoked, about $0.0000 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 2026-09-07.