What is resolve_pr_comments?

A workflow command for resolving comments on a pull request, which is a proposed change submitted for review. It groups related comments and routes them to research, code changes, replies, or explicit deferrals.

It is for capturing review threads, investigating disputed feedback, implementing accepted fixes, and recording grounded replies or decisions.

It prevents review discussions from being handled inconsistently or left without a clear outcome. It also avoids making uncertain changes when a clarifying question is safer.

resolve_pr_comments — Command by allisoneer/agentic

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/allisoneer/agentic_auxilary

Made for: Claude Code, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/resolve_pr_comments/github.svg)](https://agentmods.dev/commands/allisoneer/agentic_auxilary/resolve_pr_comments)

Your own site

<a href="https://agentmods.dev/commands/allisoneer/agentic_auxilary/resolve_pr_comments"><img src="https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/resolve_pr_comments/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/allisoneer/agentic_auxilary/resolve_pr_comments"><img src="https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/resolve_pr_comments.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,227 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.

Model	Per session	Once invoked
Fable 5.1	$0.00020	$0.02227
Opus 5.5	$0.00008	$0.00891
Sonnet 5.5	$0.00004	$0.00445
Haiku 4.5	$0.00002	$0.00223

Measured 1mo ago against content hash 0d510368d77d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 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.

.opencode/command/resolve_pr_comments.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This command should keep judgment and routing at the orchestrator level. Child sessions should do bounded work only: capture comments, research a disputed cluster, implement an accepted batch, post grounded replies, or refresh state.

The goal is to move every in-scope thread into one of these end states:

resolved by code change and reply
replied to with a grounded clarification, decline, defer, or ask-back question
waiting on reviewer response after an intentional question back in-thread
explicitly left out of scope with a documented reason

<workflow_contract>

Follow all 8 steps in order.
Use todowrite and keep exactly one task in_progress at a time.
Always start from a fresh capture artifact unless the user explicitly approves reusing an existing one.
Group related threads before choosing research, planning, implementation, or reply actions.
Prefer an in-thread clarifying question when confidence is materially low instead of forcing a shaky decision.
Choose the lightest route that still gives high confidence; if information is incomplete, consequences are unclear, or multiple plausible paths remain, escalate to research and/or planned execution rather than forcing a direct change.
Any reply that claims a code/doc/config fix must be posted only after the relevant changes are verified, committed, and pushed.
If code changes are made outside implement_plan, still require strong verification — at minimum just check and just test unless a stricter command set is clearly necessary.
Refresh comment state after material replies or code changes before declaring completion.
Do not call review_pr_comments; this workflow replaces that session-centric pattern. </workflow_contract>

<step_1>

Step 1: Interpret Intent and Establish Autonomy Bounds

Infer the requested autonomy level from <userMessage>.
Support common modifiers such as:
- pr 123
- include resolved
- humans only or robots only
- no replies yet
- dry run
- capture only
- reply only
- fix only
If the user does not narrow scope, assume:
- current PR
- unresolved comments only
- all comment sources
- autonomous routing is allowed
Ask a clarification question only if you cannot determine the target PR or if the user gave mutually exclusive instructions.
Record the explicit limits for this run, especially whether replies and code changes are allowed.

</step_1>

<step_2>

Read the full file on GitHub · 225 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.

1mo ago First seen · 225 lines · 20 tokens per session scan A 0d510368d77d

Subscribe to this mod's changes

resolve_pr_comments is a command published in the GitHub repository allisoneer/agentic_auxilary (79 stars, last pushed 6d ago), licensed MIT. It adds 20 tokens to every session and 2,227 once invoked, about $0.0001 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 2026-09-08.

Code review

resolve_pr_comments

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Step 1: Interpret Intent and Establish Autonomy Bounds

What this file has done since we first saw it

Other commands, from other repositories

refactor

review-branch

init

spec-trace-requirements

merge-conflict-analysis

boot