pr-watch-as-author

pr-watch-as-author is a skill for Claude Code, Codex from bostonaholic/team. It costs 37 tokens per session (663 once invoked), scanned A, original, MIT.

A bounded workflow that watches one of your GitHub pull requests for new review feedback for up to 24 hours. A pull request is a proposed code change awaiting review.

In plain words
What is it for?
It can remove the draft status when clearly requested, take a starting snapshot, poll for feedback, and triage new comments in review cycles.
Why use it?
It avoids repeatedly checking the pull request by hand and handles both line-specific review threads and general conversation comments.

Skill for Claude CodeCodex

Written for Claude Code and Codex: argument-hint in frontmatter, but also agents/openai.yaml present.

Part of the team plugin — 93 skills, 13 agents, 2 hooks shipped together

Good fit It can remove the draft status when clearly requested, take a starting snapshot, poll for feedback, and triage new comments in review cycles.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bostonaholic/team/pr-watch-as-author
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 bostonaholic/team --skill pr-watch-as-author
Clone the repo
git clone --depth 1 https://github.com/bostonaholic/team

Made for: Claude Code, Codex.

Or install team, the plugin that ships this one along with the rest of its 93 skills, 13 agents, 2 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-watch-as-author

README.md
[![agentmods](https://agentmods.dev/badge/skills/bostonaholic/team/pr-watch-as-author/github.svg)](https://agentmods.dev/skills/bostonaholic/team/pr-watch-as-author)
Your own site
<a href="https://agentmods.dev/skills/bostonaholic/team/pr-watch-as-author"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/pr-watch-as-author/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-watch-as-author

Your own site · 80×15
<a href="https://agentmods.dev/skills/bostonaholic/team/pr-watch-as-author"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/pr-watch-as-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 663 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 $0.00037 $0.00663
Opus 5 $0.00018 $0.00331
Sonnet 5 $0.00007 $0.00133
Haiku 4.5 $0.00004 $0.00066

Measured today against content hash e38fcfba7a0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pr-watch-as-author 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.

skills/pr-watch-as-author/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pr-watch-as-author — bounded PR review watch loop

pr-watch-as-author closes the gap between "PR open" and "ship it". It promotes the PR out of draft, takes a baseline snapshot, and polls GitHub on a bounded cycle. When new review feedback arrives, it runs the triage procedure in skills/pr-open-comments/SKILL.md. The interactive session holds the watch for 3 cycles (~90 minutes), then hands off to the scheduled pr-watch job so the session is free again. The user can interrupt at any time, and each individual command stays small and observable.

Feedback arrives in two shapes and both are triaged:

  • an inline review thread, anchored to a diff line and carrying a resolved/unresolved bit.
  • a plain PR comment on the conversation tab, carrying no resolution bit at all. Whole-PR reviews — a summary review, a bot's findings, an automated review posted as one body — land here.

The distinction matters because the unresolved-thread set cannot represent a plain comment. A comment is triaged once, keyed by its id, and is done when it has been triaged; it never joins a gate waiting to be resolved, because nothing can resolve it. Treating one as a thread would leave the watch waiting forever on a bit that does not exist; ignoring one would silently drop real feedback, which is the failure this shape is most prone to.

Procedure references

Read each reference completely when reaching that stage. Follow them in order; later stages depend on state and gates established earlier.

  1. Input
  2. Execution
  3. 1. Arm
  4. 2. Bounded cycle mechanics
  5. 3. Poll and change detection
  6. 4. On new feedback — run the triage procedure
  7. Authorized mode — apply, resolve, resume
  8. 5. Edge cases
  9. 6. Stop conditions
  10. 7. On approval — hand off, never land
  11. Compaction defense

Read the full file on GitHub · 54 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. today Changed · -8 tokens per session e38fcfba7a0b
  2. 6d ago Changed · -280 lines · -148 tokens per session cd660b578d57
  3. 7d ago Changed · +23 lines · +54 tokens per session 1722b1b05bd2
  4. 11d ago First seen · 311 lines · 139 tokens per session scan A 1a051c838b82

Subscribe to this mod's changes

pr-watch-as-author is a skill published in the GitHub repository bostonaholic/team (11 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 663 once invoked, about $0.0002 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.