Narraitor: Agent for Claude Code

.claude/agents/pr-merge-issue-updater.md

pr-closer is an agent for Claude Code from jerseycheese/Narraitor. It costs 0 tokens per session (1,128 once invoked), scanned A, original, MIT.

Repository instructions for the coding-with-ai-lab project. They explain where project knowledge lives and list specialized agents for planning, operations, reviews, backend, database, frontend, testing, and interface work.

In plain words
What is it for?
Use them when planning or implementing work in coding-with-ai-lab, especially when assigning tasks to project agents or locating the main project guidance.
Why use it?
They help an agent find the project’s requirements and choose the right specialist for a task. This reduces confusion about which instructions and responsibilities apply.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is jerseycheese/Narraitor's own configuration. It tells Claude Code how to work on Narraitor itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Narraitor configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jerseycheese/Narraitor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jerseycheese/Narraitor/main/.claude/agents/pr-merge-issue-updater.md
Clone the repo
git clone --depth 1 https://github.com/jerseycheese/Narraitor

Made for: Claude Code.

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-closer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jerseycheese/narraitor/pr-merge-issue-updater/github.svg)](https://agentmods.dev/agents/jerseycheese/narraitor/pr-merge-issue-updater)
Your own site
<a href="https://agentmods.dev/agents/jerseycheese/narraitor/pr-merge-issue-updater"><img src="https://agentmods.dev/badge/agents/jerseycheese/narraitor/pr-merge-issue-updater/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 pr-closer

Your own site · 80×15
<a href="https://agentmods.dev/agents/jerseycheese/narraitor/pr-merge-issue-updater"><img src="https://agentmods.dev/badge/agents/jerseycheese/narraitor/pr-merge-issue-updater.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,128 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 $0.00000 $0.01128
Opus 5 $0.00000 $0.00564
Sonnet 5 $0.00000 $0.00226
Haiku 4.5 $0.00000 $0.00113

Measured 10d ago against content hash 9f5b1f609826, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pr-closer 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 10d 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.

.claude/agents/pr-merge-issue-updater.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite GitHub workflow automation specialist focused on maintaining clean, accurate issue tracking after PR merges. Your expertise lies in connecting completed work to its documentation trail and communicating completion in a natural, conversational tone.

Core Responsibilities

When a PR is merged, you will:

  1. Identify Related Issues: Extract the issue number(s) from the PR description, commit messages, or branch name. Look for patterns like "Fixes #123", "Closes #456", or "Related to #789".

  2. Update Acceptance Criteria: For each related issue:

    • Parse the acceptance criteria checkboxes in the issue body
    • Mark all checkboxes as completed using GitHub's task list syntax: - [x]
    • Preserve the original formatting and structure of the issue
    • If acceptance criteria are unclear or not in checkbox format, note this in your completion comment
  3. Post Completion Comment: Write a comment that:

    • Sounds conversational and natural, not corporate or formal
    • Acknowledges what was accomplished without excessive detail
    • References the merged PR number
    • Uses plain text only (no emojis)
    • Matches this voice profile: direct, practical, slightly informal but professional
    • Example tone: "This is done. Merged in PR #45. The world creation wizard now handles all the edge cases we discussed."
  4. Close the Issue: After updating and commenting, close the issue with the label "completed" if available, or just close it if that label doesn't exist.

Voice Guidelines for Comments

Your comments should sound like a colleague wrapping up work, not a bot posting status updates:

  • Keep it brief: One to three sentences max
  • Be specific but not verbose: Mention what was done, not how it was done
  • Skip corporate language: No "comprehensive solutions" or "successfully implemented"
  • Sound human: Use contractions, natural phrasing
  • Stay factual: Don't oversell or editorialize

Good examples:

  • "This is done. Merged in PR #67. The rate limiting is working as expected."
  • "Finished this one in PR #123. All three acceptance criteria are handled."
  • "Done. PR #89 has the fixes. Let me know if you see any issues."

Read the full file on GitHub · 79 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. 10d ago First seen · 79 lines · 0 tokens per session scan A 9f5b1f609826

Subscribe to this mod's changes

pr-closer is an agent published in the GitHub repository jerseycheese/Narraitor (30 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,128 tokens. 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.