respond-to-pr-comments

respond-to-pr-comments is a skill for Claude Code from navapbc/digital-service-orchestra. It costs 100 tokens per session (2,096 once invoked), scanned A, original, Apache-2.0.

A tool that collects unresolved comments from a GitHub pull request, classifies each comment, and chooses a response action. A pull request is a proposed code change awaiting review.

In plain words
What is it for?
Use it with a pull-request URL or number to accept, defend, or defer reviewer comments and print a summary.
Why use it?
It reduces the manual work of sorting review comments and makes sure each unresolved comment receives a planned response.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; positional $N argument.

Part of the dso plugin — 37 skills, 4 commands, 53 agents shipped together

Good fit Use it with a pull-request URL or number to accept, defend, or defer reviewer comments and print a summary.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/navapbc/digital-service-orchestra/respond-to-pr-comments
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.

Any agent
npx skills add navapbc/digital-service-orchestra --skill respond-to-pr-comments
Clone the repo
git clone --depth 1 https://github.com/navapbc/digital-service-orchestra

Made for: Claude Code.

Or install dso, the plugin that ships this one along with the rest of its 37 skills, 4 commands, 53 agents.

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 respond-to-pr-comments

README.md
[![agentmods](https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/respond-to-pr-comments/github.svg)](https://agentmods.dev/skills/navapbc/digital-service-orchestra/respond-to-pr-comments)
Your own site
<a href="https://agentmods.dev/skills/navapbc/digital-service-orchestra/respond-to-pr-comments"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/respond-to-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.

agentmods 80×15 button for respond-to-pr-comments

Your own site · 80×15
<a href="https://agentmods.dev/skills/navapbc/digital-service-orchestra/respond-to-pr-comments"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/respond-to-pr-comments.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,096 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 $0.00100 $0.02096
Opus 5 $0.00050 $0.01048
Sonnet 5 $0.00020 $0.00419
Haiku 4.5 $0.00010 $0.00210

Measured 9d ago against content hash 99f660873438, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

respond-to-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 9d 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.

plugins/dso/skills/respond-to-pr-comments/SKILL.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Respond to PR Comments

Orchestrates the full comment-response pipeline for a GitHub pull request: fetches all unresolved review comments, classifies each one with an embedded LLM prompt, and dispatches the accept, defend, or defer action handler accordingly. Prints a summary table when done.

Invocation

/dso:respond-to-pr-comments <PR-URL-or-number>

Examples:

  • /dso:respond-to-pr-comments 42
  • /dso:respond-to-pr-comments https://github.com/owner/repo/pull/42

Concurrency Warning

Concurrent invocations on the same PR may both fetch comments before either has posted replies. The <!-- dso-agent-reply --> sentinel prevents double-posting on sequential runs but does NOT prevent double-processing within concurrent runs. If another invocation is running on this PR, wait for it to complete before invoking this skill.

Steps

Step 1 — Parse the PR argument

Accept either a full GitHub PR URL or a bare PR number.

If a full URL is provided, extract the PR number with:

PR_NUMBER=$(echo "$1" | grep -oE '[0-9]+$')

If a bare number is provided, use it directly. If neither pattern matches, print:

ERROR: Expected a PR number (e.g. 42) or a GitHub PR URL (e.g. https://github.com/owner/repo/pull/42).

and stop.

Step 2 — Fetch and normalize PR comments

REPO_ROOT=$(git rev-parse --show-toplevel)
NORMALIZED_JSON=$(mktemp "/tmp/dso-pr-normalized.XXXXXX")
"$REPO_ROOT/.claude/scripts/dso" pr-comment-response \
    --pr-number "$PR_NUMBER" \
    --output "$NORMALIZED_JSON"
fetch_rc=$?

If fetch_rc is non-zero, print the error from the script and stop.

Read the output:

COMMENTS_JSON=$(cat "$NORMALIZED_JSON")
COMMENT_COUNT=$(echo "$COMMENTS_JSON" | python3 -c "import sys,json; d=json.load(sys.stdin); print(len(d['comments']))")
SKIPPED_COUNT=$(echo "$COMMENTS_JSON" | python3 -c "import sys,json; d=json.load(sys.stdin); print(d.get('skipped_count',0))")

If COMMENT_COUNT is 0, print:

No unresolved comments found on PR #<PR_NUMBER>.

(including the skipped count if > 0: (N already-replied threads skipped)) and stop.

Read the full file on GitHub · 191 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. 9d ago First seen · 191 lines · 100 tokens per session scan A 99f660873438

Subscribe to this mod's changes

respond-to-pr-comments is a skill published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 100 tokens to every session and 2,096 once invoked, about $0.0005 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 2026-09-03.

Related

Other skills, from other repositories

review-implement-phase

Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.

prisma/orm · 38 tokens

engram-branch-pr

PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.

Gentleman-Programming/engram · 37 tokens

verify-behavior

Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…

nicknisi/dotfiles · 68 tokens

github-contributor

End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…

daymade/claude-code-skills · 133 tokens

revdiff

Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…

umputun/revdiff · 248 tokens

oss-maintainer

Run an open-source project's issue/PR/release loop like a careful human maintainer — triage to root cause, absorb community PRs before duplicating them, gate every merge, ship honest releases, and thank the people doing your QA for free.

debpalash/VoiceStudio · 55 tokens