receiving-pr-reviews

receiving-pr-reviews is a skill for Claude Code, Codex from bitflight-devops/skilllint. It costs 55 tokens per session (2,036 once invoked), scanned A, a copy of receiving-pr-reviews, MIT.

A workflow for handling all unanswered review comments on a GitHub pull request, which is a proposed set of code changes. It fetches review feedback, helps decide and apply fixes, sends replies, resolves threads, and checks again.

In plain words
What is it for?
Use it after pushing a pull-request commit or when asked to address reviews: inspect unresolved threads and unanswered reviews, make warranted changes, reply, resolve items, and re-check the request.
Why use it?
It reduces the chance of overlooking feedback hidden in summary reviews, inline threads, or long comment histories. It also distinguishes an empty thread list from a pull request with no reviews at all.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/bitflight-devops/skilllint/receiving-pr-reviews
Any agent
npx skills add bitflight-devops/skilllint --skill receiving-pr-reviews
Clone the repo
git clone --depth 1 https://github.com/bitflight-devops/skilllint

Made for: Claude Code, Codex.

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 receiving-pr-reviews

README.md
[![agentmods](https://agentmods.dev/badge/skills/bitflight-devops/skilllint/receiving-pr-reviews.svg)](https://agentmods.dev/skills/bitflight-devops/skilllint/receiving-pr-reviews)
Your own site
<a href="https://agentmods.dev/skills/bitflight-devops/skilllint/receiving-pr-reviews"><img src="https://agentmods.dev/badge/skills/bitflight-devops/skilllint/receiving-pr-reviews.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,036 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00055 $0.02036
Opus 5 $0.00028 $0.01018
Sonnet 5 $0.00011 $0.00407
Haiku 4.5 $0.00006 $0.00204

Measured yesterday against content hash 3166bbba7db1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

receiving-pr-reviews 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.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/pr_review_gh.py, scripts/pr_review_models.py, scripts/pr_review_threads.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

100% identical to receiving-pr-reviews — 38 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.

.agents/skills/receiving-pr-reviews/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Receiving PR Reviews

  1. Fetch every unresolved thread, every unresponded review, and Codex's approval state:

    uv run ./.agents/skills/receiving-pr-reviews/scripts/pr_review_threads.py fetch --pr <N>
    

    If the helper cannot use gh and GitHub MCP tools are available, use the lightweight GitHub MCP fallback for this workflow instead. Do not install or reconfigure gh merely to avoid the fallback, and do not run both paths for the same snapshot.

    Read reviews_count, threads_count, unresolved_count and reviewability.blockers together — never treat an empty unresolved array on its own as "nothing to do". A threads_count of 0 means no inline thread landed, not that no review landed: a top-level approval or COMMENTED review surfaces only through reviews_with_body. A non-empty blockers means the empty result set is expected and the fix is on the PR itself — undraft it, resolve the conflicts — not in the review queue.

    reviews_with_body is every review whose feedback lives in the review's own summary text rather than an inline comment. unresponded_reviews narrows that to the ones this run has not answered yet; treat every entry as actionable input. A thread's comments_truncated: true means that one thread has passed 100 comments — page its comments connection directly before concluding anything about it. For codex_approved, see step 7.

  2. For each unresolved thread or unresponded review: read it, validate the claim locally, assess against the change goal and repository instructions.

  3. Implement, commit, and push a fix only when it improves the product — push before replying, so the SHA named in the reply is inspectable and resolving the thread never outruns what is actually on the remote.

    Confirm that push's CI with checks rather than hand-writing a polling loop:

    uv run ./.agents/skills/receiving-pr-reviews/scripts/pr_review_threads.py checks --pr <N> [--timeout-seconds 270]
    

    status is passed, failed, pending, or nonepending is not green. Without --timeout-seconds this is one snapshot; with it, the command sleeps --interval-seconds between polls and returns as soon as the verdict settles. Read the whole object rather than extracting one field: none alongside reviewability.mergeable: "CONFLICTING" means checks cannot start — GitHub builds no merge ref for a conflicting PR, so no workflow runs — which is what an apparently stalled PR usually is, and no amount of waiting will change it. A draft PR is not that case: workflows do run on drafts unless a workflow opts out, so a draft blocker in reviewability.blockers says nothing about CI and checks keeps waiting through it.

    A bare none right after a push is not yet an answer — GitHub returns the same empty result before it has registered the push's workflow runs as it does for a repo with no CI. checks re-polls a none once to tell them apart, so pass --timeout-seconds when you have just pushed rather than reading the first snapshot as final.

  4. Reply on that thread with the disposition — conclusion, evidence, commit SHA, or why no change was warranted:

    uv run ./.agents/skills/receiving-pr-reviews/scripts/pr_review_threads.py reply --pr <N> --comment-id <databaseId> --body '...'
    
  5. Resolve the thread:

    uv run ./.agents/skills/receiving-pr-reviews/scripts/pr_review_threads.py resolve --thread-id <id>
    
  6. A decision spanning threads (PR sequencing, rebase disposition), or a response to a reviews_with_body/unresponded_reviews entry, goes on the PR itself via gh pr comment <N> -R <owner>/<repo> — the same owner/repo this run used in step 1 — before the work it governs. When answering a specific entry, quote that review's own url field from step 1's output in the comment body. That quoted url, postdating the review, is what clears the review out of unresponded_reviews on the next check; chronological order alone does not.

  7. Once all current threads and reviews are addressed, re-check with watch, looping short calls rather than one long block:

Read the full file on GitHub · 73 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · +15 lines 3166bbba7db1
  2. 5d ago First seen · 58 lines · 55 tokens per session scan A 6d00a5f1b48e

Subscribe to this mod's changes

receiving-pr-reviews is a skill published in the GitHub repository bitflight-devops/skilllint (7 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 2,036 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to receiving-pr-reviews, differing in 38 lines, and is treated as a copy.