wise-pr-watch-auto

wise-pr-watch-auto is a skill for Claude Code from e1024kb/wise-claude. It costs 334 tokens per session (2,524 once invoked), scanned A, original, MIT.

An automatic pull-request watcher for GitHub that monitors checks, fixes failures, and handles review comments from automated reviewers until the change is ready to merge.

In plain words
What is it for?
Use it in automated ticket-to-pull-request work to commit and push fixes, address Copilot and CodeRabbit feedback, and use an internal review when those services are unavailable.
Why use it?
It lets an unattended workflow continue through repeated test failures, bot comments, timeouts, and review decisions without stopping for user input.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the wise plugin — 38 skills, 13 agents, 1 hook, 1 MCP server shipped together

Good fit Use it in automated ticket-to-pull-request work to commit and push fixes, address Copilot and CodeRabbit feedback, and use an internal review when those services are unavailable.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add e1024kb/wise-claude
Claude Code
/plugin install wise

Made for: Claude Code.

Or install wise, the plugin that ships this one along with the rest of its 38 skills, 13 agents, 1 hook, 1 MCP server.

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 wise-pr-watch-auto

README.md
[![agentmods](https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-pr-watch-auto/github.svg)](https://agentmods.dev/skills/e1024kb/wise-claude/wise-pr-watch-auto)
Your own site
<a href="https://agentmods.dev/skills/e1024kb/wise-claude/wise-pr-watch-auto"><img src="https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-pr-watch-auto/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 wise-pr-watch-auto

Your own site · 80×15
<a href="https://agentmods.dev/skills/e1024kb/wise-claude/wise-pr-watch-auto"><img src="https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-pr-watch-auto.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 334 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,524 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 $0.00334 $0.02524
Opus 5 $0.00167 $0.01262
Sonnet 5 $0.00067 $0.00505
Haiku 4.5 $0.00033 $0.00252

Measured 2d ago against content hash ee1a6c7591fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wise-pr-watch-auto 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 2d 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/wise/skills/wise-pr-watch-auto/SKILL.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/wise-pr-watch-auto — autonomous CI watch + bulk-fix loop

Why this skill exists

/wise-pr-watch is a long interactive loop that walks review queues with the user. An unattended pipeline cannot stop to ask. /wise-pr-watch-auto runs the same job as a round loop the Lead Architect persona drives alone:

settle → gather → bulk-fix → push → re-review window → (settle …) → merge

One push per round, every handled thread resolved before that push, every wait a linear 2-minute poll that re-reads the PR state and the human-comment gate. It ends when a settled head has nothing actionable, never at "the bot posted another nit".

Copilot and CodeRabbit are review inputs, not merge gates. When one is down the loop substitutes wise's own review (review-fallback-auto.md), records it, and keeps going.

Arguments

Read $ARGUMENTS and split into whitespace-separated tokens:

  • --profile <low|medium|max> — per-run override of the session token-budget profile.

  • --minutes <n> — wall-clock budget for the whole run (default 120). n must be an integer in 1..1440 (one minute to one day). The loop stops with exhausted reason=wall-clock when it runs out.

  • The first remaining token, if present, is max_fix_attempts — the cap on commit-producing rounds. Ignore anything else.

  • A --profile / --minutes with no value, or a value out of range, is an error — stop before the loop with the matching message:

    Unknown --profile value: <value>
    Usage: /wise-pr-watch-auto [<max-fix-attempts>] [--minutes <n>] [--profile low|medium|max]
    
    Unknown --minutes value: <value> (must be an integer 1-1440)
    Usage: /wise-pr-watch-auto [<max-fix-attempts>] [--minutes <n>] [--profile low|medium|max]
    

Resolve profile: the argument if given, else the session profile via ${CLAUDE_PLUGIN_ROOT}/references/profile-read.md (silent degrade to medium). The profile scales budget only — never gates, verdicts or merge rules:

profile max_fix_attempts default fixer tier Opus model (opus_model)
low 3 prefer sonnet-grade focus claude-opus-4-8 (MUST — never Opus 5)
medium 10 today's defaults opus
max 10 today's defaults opus

Read the full file on GitHub · 192 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. 2d ago Changed · -4 lines · +23 tokens per session ee1a6c7591fe
  2. 3d ago Changed · +20 lines 046c94b8a711
  3. 4d ago Changed · +3 lines 90529ab536ae
  4. 9d ago First seen · 173 lines · 311 tokens per session scan A 212887591bda

Subscribe to this mod's changes

wise-pr-watch-auto is a skill published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed today), licensed MIT. It adds 334 tokens to every session and 2,524 once invoked, about $0.0017 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 skills, from other repositories

release

Bump a plugin's version, write a detailed changelog entry for the upgrade skill to consume, and commit+push. Takes a plugin slug argument identifying which plugin under plugins/ to release. Use this skill whenever the user says "release", "version bump", "cut a release", "changelog and push", or finishes a set of…

gtapps/claude-code-hermit · 104 tokens

pre-release-review

Run the pre-release gate for this multi-plugin monorepo: establish each plugin's release boundary from its last reachable tag to HEAD, audit every changed plugin's [Unreleased] changelog against the actual code diff, identify contract-surface and breaking changes, and, per the objective the user picks up front, either…

gtapps/claude-code-hermit · 188 tokens

commit

Changelog and commit — lightweight motion for day-to-day plugin dev work in the monorepo. One commit per plugin scope; CHANGELOG and staging routed by detected slug. Trigger when the user says "commit", "commit this", "save this", "wrap this up", "let's commit", or finishes a change and wants to capture it. NOT for…

gtapps/claude-code-hermit · 90 tokens

fleet-release

Use this skill whenever the user wants to release, ship, prep, or cut versions for two or more plugins together on the current branch. Trigger on phrasings like "release both plugins", "ship them together", "release all changed plugins", "fleet release", "multi-plugin release", "release in order", or "release…

gtapps/claude-code-hermit · 96 tokens

spawn-session

Spawn a background Claude Code helper in its own git worktree, watch it until idle, and relay its report to the operator. Use when the operator says "spawn a helper", "spawn-session", "run this in a background session", or names /spawn-session.

gtapps/claude-code-hermit · 57 tokens

github-pr-creation

Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…

fvadicamo/dev-agent-skills · 75 tokens