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.
/plugin marketplace add e1024kb/wise-claude/plugin install wiseWrote 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.
[](https://agentmods.dev/skills/e1024kb/wise-claude/wise-pr-create-auto)<a href="https://agentmods.dev/skills/e1024kb/wise-claude/wise-pr-create-auto"><img src="https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-pr-create-auto.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00136 | $0.01008 |
| Opus 5 | $0.00068 | $0.00504 |
| Sonnet 5 | $0.00027 | $0.00202 |
| Haiku 4.5 | $0.00014 | $0.00101 |
Grade A, and why
wise-pr-create-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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/wise-pr-create-auto — create or refresh a PR, autonomously
Why this skill exists
/wise-pr-create is interactive — it asks the user to pick the base
branch. An unattended ticket→PR pipeline can't stop to ask.
/wise-pr-create-auto is the decision-free variant: it picks the
repo's default branch as the base and never calls AskUserQuestion.
It is also the reusable building block the ticket-auto workflow's
PR-create step follows.
Arguments
This skill takes no arguments. Ignore anything the user types beyond the skill name.
Run on another harness (--on)
If $ARGUMENTS contains --on <harness>[:<model>[:<effort>]] (or
--on ask / a bare --on), do
NOT run the procedure below in this conversation. Strip the --on
tokens (everything left is SKILL_ARGS), then read
${CLAUDE_PLUGIN_ROOT}/references/dispatch.md and follow it with:
SKILL_MD=${CLAUDE_PLUGIN_ROOT}/skills/wise-pr-create-auto/SKILL.mdSKILL_ARGS= the remaining tokens
--on ask (or a bare --on) picks harness, model and effort through
one composite AskUserQuestion before any child spawns — the ONE
sanctioned prompt in this skill: it happens at invocation time, so the
dispatched run itself stays decision-free.
The reference probes the harness login, validates model and effort
against the engine catalog, and runs the procedure as a headless child
via engine.sh dispatch; you only relay its result. Without --on,
this section does not apply.
Procedure
1. Resolve the project + branch
git rev-parse --show-toplevel
git rev-parse --abbrev-ref HEAD
Use the toplevel as project.path and the branch as
current_branch.
2. Follow the shared fragment
Read ${CLAUDE_PLUGIN_ROOT}/workflows/ticket-auto/prompts/ensure-pr-auto.md
and follow it end to end with current_branch and project.path.
The fragment detects PR state, drafts the body (via
references/pr/draft-body.md), and creates or refreshes the
PR with the repo default branch as base. The drafting step mandates
reading ${CLAUDE_PLUGIN_ROOT}/skills/wise-human-writing/SKILL.md —
the body follows those human-first rules; do not skip that read.
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.
- yesterday Changed · +21 lines daa9c9e919af
- 7d ago First seen · 73 lines · 136 tokens per session scan A 9a62e0fa124e
wise-pr-create-auto is a skill published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed yesterday), licensed MIT. It adds 136 tokens to every session and 1,008 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.
Other skills, from other repositories
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…
open-pr
Use this skill to submit the commits on the current branch as one pull request against a GitHub repository. Push the branch, open the PR with an imperative title and a body that names what changed and why, and post a follow-up ping only when CODEOWNERS resolves to one person. One branch per run, one pull request per…
merge-quiz
Before merging or deploying the output of a long session, generate a change report with a comprehension quiz the user must pass. Use whenever the user says "merge", "deploy", "we're done", "wrap up", or at the end of any session that modified more than 150 lines or touched production-relevant code. Also invocable as…
fix-pr
Reads all unresolved review comments and threads on a change (PR/MR) — and its failing CI checks, which count as feedback too — implements the fixes, pushes, and replies to each thread. Tracker- and host-agnostic — GitHub via gh is the factory default; docs/agents/code-host.md overrides. Use when user says "fix pr…
quick-wrap
Short session close: commit, handle loose ends, stop. Not workstream-complete.
merging-to-main
Keyword-gated by name. Merges a ready branch to main: PR, CI, cleanup.