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.
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.
git clone --depth 1 https://github.com/microsoft/copilot-for-eclipseWrote 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/commands/microsoft/copilot-for-eclipse/resolve-pr-comments)<a href="https://agentmods.dev/commands/microsoft/copilot-for-eclipse/resolve-pr-comments"><img src="https://agentmods.dev/badge/commands/microsoft/copilot-for-eclipse/resolve-pr-comments.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.01221 |
| Opus 5 | $0.00006 | $0.00611 |
| Sonnet 5 | $0.00003 | $0.00244 |
| Haiku 4.5 | $0.00001 | $0.00122 |
Grade A, and why
resolve-pr-comments scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review Comment Resolution
Resolve PR review comments for PR #${input:pr_number:Enter PR number}
Critical Rules
SEQUENTIAL PROCESSING IS MANDATORY: You MUST fully complete ALL steps for one comment before starting the next.
CONFIRMATION GATES ARE BLOCKING: You MUST wait for explicit user confirmation at each gate. Do NOT proceed without user approval.
TODO TRACKING: Use the todo list to track progress. Only ONE comment should be "in-progress" at a time.
Workflow
1. Verify Branch
- Check current branch:
git branch --show-current - If not on the PR's source branch, switch to it:
gh pr checkout ${input:pr_number}
2. Get All Review Comments and Save to File
Use pagination to retrieve all comments (gh CLI defaults to 30 results) and save to a file for reference:
mkdir -p .github/pullrequests/${input:pr_number}
gh api repos/microsoft/copilot-for-eclipse/pulls/${input:pr_number}/comments --paginate --jq '.[] | {id: .id, path: .path, line: .line, body: .body, in_reply_to_id: .in_reply_to_id, user: .user.login}' > .github/pullrequests/${input:pr_number}/comments.json
Note: The line field from the API points directly to the line in the current file where the comment was made. No diff parsing is needed - just read the file at that line number to see the code context.
3. Filter and Classify Comments
After fetching comments:
- Identify resolved comments - If a comment has replies (other comments with
in_reply_to_idmatching itsid) from the PR author starting with "Done." or similar, it's already resolved - Skip reply comments - Comments with
in_reply_to_idset are replies, not original review comments - Focus on actionable review comments - Only create TODOs for original comments (no
in_reply_to_id) that haven't been resolved
4. For Each Actionable Comment, Extract:
id: The comment ID (needed for replying)path: The file path where the comment was madeline: The line number in the file (use this directly to read code context)body: The actual review comment contentin_reply_to_id: If set, this is a reply to another comment (skip these)user: The username who made the comment
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 · 13 tokens per session scan A 705262d412e5
resolve-pr-comments is a command published in the GitHub repository microsoft/copilot-for-eclipse (122 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 1,221 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.
Other commands, from other repositories
devkit.github.review-pr
Provides comprehensive GitHub pull request review with code quality, security, and best practices analysis. Use when reviewing a PR before merging.
speckit.spex.submit
Push and create PR for team review, with optional watch mode for CI monitoring.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
code-review
Code review for branch changes. Analyzes git diff between branches with multi-level depth (low/medium/high). Matches changes against task description. Returns structured report with severity levels and verdict.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.