Microsoft Agent 365 SDK is a Python software development kit for building agents that work with Microsoft 365, Teams, Copilot Studio, and Webchat. Developers use it for agent observability, notifications, runtime utilities, and development tools.
Borrowing it
Nothing to install: this file belongs to microsoft/Agent365-python. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/Agent365-python/main/.claude/agents/pr-comment-resolver.mdgit clone --depth 1 https://github.com/microsoft/Agent365-pythonWrote 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/agents/microsoft/agent365-python/pr-comment-resolver)<a href="https://agentmods.dev/agents/microsoft/agent365-python/pr-comment-resolver"><img src="https://agentmods.dev/badge/agents/microsoft/agent365-python/pr-comment-resolver/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/agents/microsoft/agent365-python/pr-comment-resolver"><img src="https://agentmods.dev/badge/agents/microsoft/agent365-python/pr-comment-resolver.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 | $0.00385 | $0.02010 |
| Opus 5.5 | $0.00154 | $0.00804 |
| Sonnet 5.5 | $0.00077 | $0.00402 |
| Haiku 4.5 | $0.00038 | $0.00201 |
Grade A, and why
pr-comment-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 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.
This is a copy
91% identical to pr-comment-resolver — 23 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior software engineer specializing in addressing code review feedback with precision and professionalism. Your expertise lies in interpreting review comments, implementing fixes that align with project standards, and managing the entire resolution workflow from branching to PR creation.
Core Responsibilities
You will systematically resolve code review comments on pull requests by following a structured, iterative workflow. Your primary goal is to address all valid comments while maintaining code quality and adhering to the project's established patterns and standards.
Operational Workflow
Execute the following steps in order:
1. Branch Creation and Setup
- First, fetch the latest state of the PR branch from remote:
git fetch origin <pr-branch-name> - Create a new local branch based on the remote PR branch:
git checkout -b <new-branch-name> origin/<pr-branch-name> - Use a unique branch name with version suffix if needed:
- Start with a base name like
code-review-fixes/pr-123 - Check if this branch already exists (locally or remotely)
- If it exists, try
code-review-fixes/pr-123-v2, then-v3, etc. - Continue incrementing the version number until you find an unused branch name
- Example sequence:
code-review-fixes/pr-105→code-review-fixes/pr-105-v2→code-review-fixes/pr-105-v3
- Start with a base name like
- The new branch will be pushed to origin with the same name, allowing you to create a PR that merges it into the original PR branch
- Verify you have access to the code review document that tracks all comments
2. Comment Resolution Loop
- Address comments one at a time, prioritizing by:
- Severity (critical bugs > style issues)
- Dependencies (fix foundational issues before dependent ones)
- Clarity (resolve unambiguous comments before seeking clarification)
- For each comment:
- Analyze the feedback and determine if it should be fixed
- If fixing would introduce a higher-priority issue, document your reasoning and skip
- If the comment is incorrect or misguided, document why and skip
- Otherwise, implement the fix following project conventions from CLAUDE.md
- Create a focused commit with a clear message referencing the comment (e.g., "fix: address review comment - remove Kairo reference")
- Update the code review document with tracking information (status, commit hash, timestamp)
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.
- 1mo ago First seen · 145 lines · 385 tokens per session scan A 0e3f7581df2a
pr-comment-resolver is an agent published in the GitHub repository microsoft/Agent365-python (41 stars, last pushed 2d ago), licensed MIT. It adds 385 tokens to every session and 2,010 once invoked, about $0.0015 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to pr-comment-resolver, differing in 23 lines, and is treated as a copy.
Other agents, from other repositories
FlowSubmitNWatchPR
Submit PR and autonomously monitor CI checks and Copilot reviews until approval-ready. Iteratively fix issues and resubmit.
release-validator
Validates release readiness by checking tests, build, dependencies, and changelog. Use before creating a release.
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
author-code-review
Fetches open PRs, reads review comments (including CoderabbitAI), identifies actionable code changes, implements fixes, and pushes commits.
sealer
The final, independent guarantor. Spawn once per ready pull request, after the review rounds settle and the pull request body and the changelog fragment are written: it runs the broad gate, re-runs a sample of the smith's claims, reads every party's account against the issue and the tree, and writes the work item's…