pr-narrator

pr-narrator is an agent for coding agents from orin-dx/agent-plugins. It costs 140 tokens per session (851 once invoked), scanned A, original, MIT.

A subagent that writes a pull request title and description from staged or committed changes, optionally using a linked specification or requirement.

In plain words
What is it for?
It helps prepare an imperative title, summary, rationale, test checklist, labels, and required links or breaking-change notes.
Why use it?
It turns a code diff into review-oriented context, so the pull request explains the purpose and testing plan instead of merely listing changed files.

Agent

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 agents/orin-dx/agent-plugins/pr-narrator
Clone the repo
git clone --depth 1 https://github.com/orin-dx/agent-plugins
Per session 140 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 851 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00140 $0.00851
Opus 5 $0.00070 $0.00426
Sonnet 5 $0.00028 $0.00170
Haiku 4.5 $0.00014 $0.00085

Measured today against content hash bd4c606b2045, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pr-narrator 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 today.

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/courier/agents/pr-narrator.md · 57 lines

What it actually says

<load_first> shared/references/github.md </load_first>

Key failure modes:

  • The body is a reformatted diff.
  • The test plan says "run the tests."
{
  "title": "string (imperative mood, under 70 chars — conventional commit subject style)",
  "body": "string (markdown — Summary as 1-3 bullets, then Why, then Test Plan as a checklist; matches the PR template and Voice section in shared/references/github.md)",
  "labels": ["string"],
  "reasoning": "string"
}

reasoning is a scratchpad — explain the framing decisions made. It is not forwarded downstream.

WHEN a spec or requirement is linked, NEVER omit the link from the PR body. IF breaking changes are present, they MUST appear in the PR body under their own heading. NEVER summarize the diff as the body — the body must explain purpose, not contents. THE SYSTEM SHALL structure body as summary bullets first and a test-plan checklist last, per shared/references/github.md's template and Voice section — never a single prose block. NEVER exceed 3 summary bullets — if the change needs more than 3 to explain its purpose, the change's scope is the problem, not the bullet count.

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. today Changed · +4 lines bd4c606b2045
  2. 3d ago First seen · 53 lines · 140 tokens per session scan A 0e90d2d265a0

Subscribe to this mod's changes

pr-narrator is an agent published in the GitHub repository orin-dx/agent-plugins (1 stars, last pushed today), licensed MIT. It adds 140 tokens to every session and 851 once invoked, about $0.0007 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 2026-08-31.

Related

Other agents, from other repositories