datagsm-server: Skill for Claude Code

.agents/skills/write-pr/SKILL.md

write-pr is a skill for Claude Code from themoment-team/datagsm-server. It costs 41 tokens per session (611 once invoked), scanned A, original, MIT.

A workflow that creates a GitHub pull request from the commits and changes on the current branch. It prepares a title, description, labels, and the final pull request.

In plain words
What is it for?
Use it to inspect the branch, choose labels, generate pull-request text, and open the pull request on GitHub.
Why use it?
It removes the manual work of reviewing branch changes and formatting a pull request to match repository rules.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is themoment-team/datagsm-server's own configuration. It tells Claude Code how to work on datagsm-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything datagsm-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to themoment-team/datagsm-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/themoment-team/datagsm-server/master/.agents/skills/write-pr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/themoment-team/datagsm-server

Made for: Claude Code.

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 write-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/themoment-team/datagsm-server/write-pr/github.svg)](https://agentmods.dev/skills/themoment-team/datagsm-server/write-pr)
Your own site
<a href="https://agentmods.dev/skills/themoment-team/datagsm-server/write-pr"><img src="https://agentmods.dev/badge/skills/themoment-team/datagsm-server/write-pr/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 write-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/themoment-team/datagsm-server/write-pr"><img src="https://agentmods.dev/badge/skills/themoment-team/datagsm-server/write-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 611 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 $0.00041 $0.00611
Opus 5.5 $0.00016 $0.00244
Sonnet 5.5 $0.00008 $0.00122
Haiku 4.5 $0.00004 $0.00061

Measured 29d ago against content hash 3252f80fb82c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

write-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 29d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/create-pr.sh, scripts/discover-domains.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/write-pr/SKILL.md · 69 lines

What it actually says

Step 1 — Gather Context

git branch --show-current
git log origin/develop..HEAD --oneline 2>/dev/null || git log --oneline -15
git diff origin/develop...HEAD --stat 2>/dev/null || git diff HEAD~5...HEAD --stat
git diff origin/develop...HEAD 2>/dev/null || git diff HEAD~5...HEAD

Also read the PR template:

cat .github/PULL_REQUEST_TEMPLATE.md

Step 2 — Determine Labels

Read references/labels.md and select 1–2 appropriate labels based on the nature of the changes. Read references/commit-conventions.md for commit type and scope naming rules.

Step 3 — Generate PR Content

Title — Generate 3 options in the format [scope] description:

  • Scope: determine from changed files — run sh scripts/discover-domains.sh to get the current domain list, then pick the one matching the changes. Use [global] / [ci/cd] for cross-cutting changes only. Wrap in brackets: [auth], [student], etc.
  • Description: Korean, concise, no emojis, max 50 characters total
  • Wrap class names, method names, annotations, and technical terms in backticks (e.g., @Transactional, StudentServiceImpl)

Body — Follow the .github/PULL_REQUEST_TEMPLATE.md structure:

  • Korean 합쇼체: ~하였습니다, ~되었습니다, ~추가하였습니다
  • No emojis
  • Max 2500 characters
  • Wrap all proper nouns and technical identifiers in backticks: class names, method names, annotations, file names, field names, config keys, module names

Step 4 — Write Body & Show Preview

Write the body to PR_BODY.md, then display:

## PR 제목 후보
1. [title1]
2. [title2]
3. [title3]

## 선택된 라벨
- label1, label2

## PR 본문 미리보기
[body content]

Ask the user which title to use (present options 1/2/3). Wait for the answer before proceeding.

Step 5 — Create PR

Run the creation script with the confirmed title and labels:

bash scripts/create-pr.sh "<confirmed-title>" "PR_BODY.md" "<label1>,<label2>"

After creation, display the PR URL. Cleanup: remove PR_BODY.md.

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 29d ago First seen · 69 lines · 41 tokens per session scan A 3252f80fb82c

Subscribe to this mod's changes

write-pr is a skill published in the GitHub repository themoment-team/datagsm-server (29 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 611 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-08.

Related

write-pr compared with skills from other repositories

write-pr next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
write-prthemoment-team/datagsm-serverSkill29yesterdayMITA41Claude Code
plugin-code-review-orchestratedexplyt/spring-pluginSkill167yesterdayApache-2.0A72Claude Code, Codex
review-scope-resolverexplyt/spring-pluginSkill167yesterdayApache-2.0A83Claude Code, Codex
spring-plugin-issue-deliveryexplyt/spring-pluginSkill167yesterdayApache-2.0A176Claude Code, Codex
develop-inspection-featureexplyt/spring-pluginSkill167yesterdayApache-2.0A103Claude Code, Codex
spring-ecosystem-docspledgeandgrow/pledge-skillsSkill103mo agoMITA43Claude Code, Codex
shepherdchrisbanes/skillsSkill1.1kyesterdayApache-2.0A37Claude Code, Codex