draft-pr

A tool that writes a pull request (PR) title and description from a branch’s commits, work plan, and recorded checks. A PR is a proposed code change submitted for review before it is merged.

In plain words
What is it for?
Use it when preparing a PR or asking for its description. It writes the result to `.workflow/pr.md` and adjusts the amount of detail to the size of the change.
Why use it?
It gathers the relevant change and verification details into one consistent description. It also avoids claiming checks or planning work that was never recorded.

Skill for Claude CodeCodex

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 skills/matheuspavaneli/workbench/draft-pr
Any agent
npx skills add matheusPavaneli/workbench --skill draft-pr
Clone the repo
git clone --depth 1 https://github.com/matheusPavaneli/workbench

Made for: Claude Code, Codex.

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 775 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 $0.00042 $0.00775
Opus 5 $0.00021 $0.00387
Sonnet 5 $0.00008 $0.00155
Haiku 4.5 $0.00004 $0.00077

Measured yesterday against content hash f30ed2f16a80, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

draft-pr 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.

skills/draft-pr/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

draft-pr

python "${CLAUDE_PLUGIN_ROOT}/lib/wb.py" <args>

This skill writes the description. Opening the PR is the user's call.

Steps

  1. Assemble the inputs. pr context <KEY>. One call returns the branch and base, the commits on it, the changed files, the critical zones, the plan's summary and open questions, the verification verdict with each command's exit code, and a shape telling you how much description this change earns. For a PR onto a validation branch: pr context <KEY> --target homolog.

  2. Check _missing. If it lists plan or verification, that artifact does not exist. Say so in the description — do not write around the gap and do not claim a check that was never run.

  3. Write the title in the repo's commit style (commit convention if you have not already). One line, imperative, specific enough that a reviewer scanning a list knows what this is.

  4. Write only the shape you were given. trivial is a title and one sentence, no headings at all. small is What and Verification. Only large earns the full template, and even then a section with nothing to say is deleted rather than left as an empty heading.

    ## What
    One or two sentences. What changes, and why now.
    
    ## Why
    The problem, with the ticket link. Skip if the title says it.
    
    ## How
    Only the decisions a reviewer cannot infer from the diff — a trade-off, an
    approach considered and dropped, a constraint that forced the shape.
    
    ## Verification
    The actual commands and their results, from `pr context`.
    
    ## Risk and rollback
    Critical zones touched, and how to undo this.
    
    ## Open questions
    From the plan. An empty section is better deleted than left blank.
    
  5. Check and save. pr check --file <path> --shape <shape> rejects empty sections, placeholders, unticked boxes and filler. Then save to .workflow/<KEY>/pr.md and show it.

  6. Close the ticket if the backlog is local: task done <KEY>. A real tracker owns its own state, and wb refuses there rather than recording a status only this checkout believes. Say the PR is open, not that it merged.

Read the full file on GitHub · 77 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. yesterday First seen · 77 lines · 42 tokens per session scan A f30ed2f16a80

Subscribe to this mod's changes

draft-pr is a skill published in the GitHub repository matheusPavaneli/workbench (1 stars, last pushed 10d ago), licensed MIT. It adds 42 tokens to every session and 775 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 2026-08-31.

Related

Other skills, from other repositories

integration-rule-engine

A declarative routing engine that turns ticket / error attributes (reporter, label, project, area path, error class, environment) into a tag + AI agent + priority assignment, so cross-source workflows ("security tickets always go to the OWASP reviewer") stay out of code and in user-editable rules.

aozyildirim/Agena · 67 tokens

stale-ticket-triage

Replace the weekly "look at every ticket older than X days" meeting with a scheduled AI scan that picks close / snooze / keep per ticket plus a one-sentence reason, so a PM can bulk-approve in 90 seconds Monday morning.

aozyildirim/Agena · 57 tokens

azure-devops

Manage Azure DevOps projects, work items, repos, PRs, pipelines, wikis, test plans, security alerts, variable groups, environments/approvals, branch policies, and attachments. Use when user asks to: manage sprints, create/update work items, list repos, create PRs, run pipelines, search code, manage wiki pages, check…

sanjay3290/ai-skills · 105 tokens

apple-container

Apple's open-source container CLI to build, run, and manage OCI/Linux containers as lightweight per-container VMs on Apple-silicon macOS — no Docker daemon required. Use when the user mentions the container CLI, "apple container", running or building containers on macOS without Docker/Podman, container run, container…

sanjay3290/ai-skills · 146 tokens

atlassian

Manage Jira issues and Confluence wiki pages in Atlassian Cloud. Use when: (1) searching/creating/updating Jira issues with JQL, (2) searching/reading/creating Confluence pages with CQL, (3) managing Jira workflows, transitions, and comments, (4) browsing Confluence spaces and page hierarchies. Supports OAuth 2.1 via…

sanjay3290/ai-skills · 96 tokens

google-calendar

Interact with Google Calendar - list calendars, view events, create/update/delete events, and find free time. Use when user asks to: check calendar, schedule a meeting, create an event, find available time, list upcoming events, delete or update a calendar event, or respond to meeting invitations. Lightweight…

sanjay3290/ai-skills · 76 tokens