pr-comment-responder

pr-comment-responder is an agent for Claude Code from rjmurillo/ai-agents. It costs 59 tokens per session (20,070 once invoked), scanned A, original, MIT.

An agent that coordinates responses to pull-request review comments, which are feedback messages attached to proposed code changes.

In plain words
What is it for?
Collecting pull-request context, triaging feedback, tracking discussion threads, delegating implementation, and checking that comments were addressed.
Why use it?
It keeps every reviewer comment acknowledged, classified, tracked, and connected to a resolution.

Agent for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; names the TodoWrite tool; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the project-toolkit plugin — 95 skills, 26 commands, 33 agents, 4 hooks shipped together

Good fit Collecting pull-request context, triaging feedback, tracking discussion threads, delegating implementation, and checking that comments were addressed.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add rjmurillo/ai-agents
Claude Code
/plugin install project-toolkit

Made for: Claude Code.

Or install project-toolkit, the plugin that ships this one along with the rest of its 95 skills, 26 commands, 33 agents, 4 hooks.

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 pr-comment-responder

README.md
[![agentmods](https://agentmods.dev/badge/agents/rjmurillo/ai-agents/pr-comment-responder.svg)](https://agentmods.dev/agents/rjmurillo/ai-agents/pr-comment-responder)
Your own site
<a href="https://agentmods.dev/agents/rjmurillo/ai-agents/pr-comment-responder"><img src="https://agentmods.dev/badge/agents/rjmurillo/ai-agents/pr-comment-responder.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 20,070 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 $0.00059 $0.20070
Opus 5 $0.00030 $0.10035
Sonnet 5 $0.00012 $0.04014
Haiku 4.5 $0.00006 $0.02007

Measured yesterday against content hash 0e00e1b130be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pr-comment-responder 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.

.claude/agents/pr-comment-responder.md · 2,117 lines

How it starts

The opening of the file, as written. The whole thing — 2,117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Comment Responder Agent

Core Identity

PR Review Coordinator that gathers PR context, tracks comments, and delegates to orchestrator for analysis and implementation. This agent is a thin coordination layer focused on:

  1. Gathering complete PR context efficiently
  2. Tracking all comments with acknowledgment
  3. Delegating analysis to orchestrator (no custom routing logic)
  4. Managing reviewer communication
  5. Ensuring all comments are addressed

Style Guide Compliance

Key requirements:

  • No sycophancy, AI filler phrases, or hedging language
  • Active voice, direct address (you/your)
  • Replace adjectives with data (quantify impact)
  • No em dashes, no emojis
  • Text status indicators: [PASS], [FAIL], [WARNING], [COMPLETE], [BLOCKED]
  • Short sentences (15-20 words), Grade 9 reading level

Agent-Specific Requirements:

  • Direct, actionable responses
  • No sycophantic acknowledgments
  • Evidence-based explanations
  • Text status indicators: [DONE], [WIP], [WONTFIX]

Comment Map Status Vocabulary

Every comment in comments.md carries exactly one status from this table. This table is the only place the vocabulary is defined. Every gate derives its counts from it.

Status Meaning Terminal
[NEW] Fetched, not yet acknowledged No
[ACKNOWLEDGED] Reaction posted, fix not yet committed No
[COMPLETE] Fix committed and pushed Yes
[WONTFIX] Explicitly decided not to change Yes
[DUPLICATE] Same point already resolved by another comment Yes
[DEFERRED] Refs #<issue> Tracked in a filed issue, not fixed in this PR Yes, only with the Refs #<issue> suffix

Comment map fields render as **Status**: [NEW], so every status grep must match the bold field at line start. Dropping the ** delimiters or the ^ anchor matches nothing and reports zero.

[DEFERRED] is terminal only when the status line carries an inline Refs #<issue> reference, as in **Status**: [DEFERRED] Refs #4054. A bare [DEFERRED] names no tracking issue, so nobody can find the work later and the gate keeps it pending.

Read the full file on GitHub · 2,117 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 Changed · -1 lines 0e00e1b130be
  2. 2d ago Changed 3ef97295deeb
  3. 7d ago First seen · 2,118 lines · 59 tokens per session scan A 66dc8d968040

Subscribe to this mod's changes

pr-comment-responder is an agent published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 20,070 once invoked, about $0.0003 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 2026-08-30.

Related

Other agents, from other repositories

code-reviewer

A code-review agent that checks whether changes follow their specification and assesses code quality, security, maintainability, and performance. It reports findings with severity levels and file-and-line references.

sangrokjung/claude-forge · 96 tokens

security-reviewer

A read-only security review agent that checks code for common web risks, exposed secrets, unsafe input handling, authentication and authorization problems, and dependency issues. OWASP Top 10 is a widely used list of major web application security risks.

sangrokjung/claude-forge · 95 tokens

stackhawk-security-onboarding

Automatically set up StackHawk security testing for your repository with generated configuration and GitHub Actions workflow.

archubbuck/workspace-architect · 25 tokens

python-ml-architect

Python ML (PyTorch/scikit-learn) architecture specialist. Validates data/model/training/evaluation/inference layering, config-driven hyperparameters, reproducibility discipline, and pipeline separation. Dispatch when touching model definitions, training loops, datasets, or inference code.

onlygian/G-Forge · 59 tokens

python-cli-architect

Python CLI (Click/Typer) architecture specialist. Validates command/service layering, arg-parsing discipline, Rich output usage, and Pydantic Settings config. Dispatch when touching CLI commands, services, config, or output formatting.

onlygian/G-Forge · 51 tokens

sveltekit-architect

SvelteKit architecture specialist. Validates load function placement, form action patterns, store design, and file-based routing conventions. Dispatch when touching routes, load functions, form actions, or shared lib code.

onlygian/G-Forge · 47 tokens