A workflow for shipping repository changes as a pull request, including issue linking, commits, pushing a branch, and writing the description. It requires reading the full change and reporting real verification results.

Use it to create or update a pull request, prepare its commit and branch, link the work to an issue, and document implementation and checks.

It prevents incomplete pull requests, missing tracking issues, accidental inclusion of unrelated files, and misleading review information.

How ccch1mneyyy/dsh-TUI configures Claude Code and Codex

About the project

dsh-TUI is a terminal interface plugin for DeepSeek Harness that gives the coding agent a Claude Code-style display with live status, streaming thoughts, rollback, context usage, and TPS information. It is for users who prefer a richer terminal workflow, and the catalogue entries extend the DeepSeek Harness environment with related skills and instructions.

ccch1mneyyy/dsh-TUI · 5,919 stars · on GitHub · dshtui.com

Reuse

Borrowing it

Nothing to install: this file belongs to ccch1mneyyy/dsh-TUI. 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/ccch1mneyyy/dsh-TUI/main/.agents/skills/pr/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/ccch1mneyyy/dsh-TUI

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ccch1mneyyy/dsh-tui/pr/github.svg)](https://agentmods.dev/skills/ccch1mneyyy/dsh-tui/pr)

Your own site

<a href="https://agentmods.dev/skills/ccch1mneyyy/dsh-tui/pr"><img src="https://agentmods.dev/badge/skills/ccch1mneyyy/dsh-tui/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ccch1mneyyy/dsh-tui/pr"><img src="https://agentmods.dev/badge/skills/ccch1mneyyy/dsh-tui/pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 568 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.

Model	Per session	Once invoked
Fable 5.1	$0.00034	$0.00568
Opus 5.5	$0.00014	$0.00227
Sonnet 5.5	$0.00007	$0.00114
Haiku 4.5	$0.00003	$0.00057

Measured 28d ago against content hash d94edd5a2905, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 28d 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.

.agents/skills/pr/SKILL.md · 18 lines

What it actually says

Ship the current change as a pull request a reviewer can understand from the description alone: why it exists, the shape of the implementation, and what was actually verified.

Make sure a code PR has a closing issue: the issue-link CI check fails one without it. Docs-only PRs and PRs a maintainer labels no-issue-needed are exempt (docs/contributing.md). Reuse the issue the work came from; when there is none, open a tracking issue first — title [功能]/[Bug] …, body with 目标, 范围, and 非目标 sections, as in #919 — and link it.
Commit and push. Title the commit and the PR in English, type(scope): summary (conventional commits, as in #1110); the commit body is English too. Stage explicit paths only, leave lib/ and unrelated worktree changes out, and push a branch whose upstream is itself, never main. Reuse the PR already open for the branch (gh pr view) instead of opening a second one.
Read the complete diff against the base, the linked issue, and enough surrounding code to explain ownership and behavior. Collect the verification you actually ran; run what docs/contributing.md requires for the changed area when it has not run yet.
Write the body from .github/PULL_REQUEST_TEMPLATE.md, following the HTML comments in it and then deleting them:
- Why the change is exactly one sentence.
- Special things to note holds 1–3 reviewer warnings; deliberate divergences, omissions, and unrun checks go here.
- Change outline is a visual outline, not prose or a file-by-file changelog: the smallest set of views — file tree, call or data flow, key shapes — each beside one short sentence, diff for a changed shape and a full block for a new one. For a terminal-visible change include the real rendered screen as a text block, captured headlessly the way the scripts/verify-*.tsx regressions render (renderToScreen or an @xterm/headless terminal).
- Verification lists the commands that ran and their results. Write the body in Chinese, plainly, one person to another.
Publish with gh pr create --body-file or gh pr edit --body-file, then confirm the rendered body with gh pr view. Report the PR URL, the linked issue, and the CI state.

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.

28d ago First seen · 18 lines · 34 tokens per session scan A d94edd5a2905

Subscribe to this mod's changes

pr is a skill published in the GitHub repository ccch1mneyyy/dsh-TUI (5,919 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 568 once invoked, about $0.0001 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 2026-09-29.

Claude Code Code review Commits Git and workflow coding-agent deepseek deepseek-harness dsh-plugin ink

github-publish-changes

Publish intentional local changes by confirming scope, creating a branch when needed, staging selected files, committing, pushing, and creating a Draft Pull Request through the connected GitHub service.

Devin-AXIS/iPolloWork · 41 tokens

gh-publish

Publish task-scoped changes to GitHub through a branch/commit/push/PR flow, including fork-based external contributions. Use when the user wants changes pushed or a PR opened; draft PR is the default.

Starfie1d1272/dsh-github-skills · 47 tokens

code-review-zh

A Git-based code review workflow that compares changes from a chosen commit, branch, tag, or merge point. It checks both whether the code follows the repository's written standards and whether it implements the requested specification.

gongyijie85/mattpocock-skills-dsh-zh · 109 tokens

pr-draft-summary

Plan, implement, or review pr draft summary work in an existing codebase with compatibility, security, and verification controls. Use when the user explicitly requests pr draft summary work.

sandbaseai/sandbase-skills · 40 tokens

autofix-pr

Watch a pull request and fix it from a worktree of its own - CI failures, review feedback from trusted authors and merge conflicts are fixed, pushed to the PR branch and answered on the PR under the user's git and gh identity. Usage - /autofix-pr [ | ] [--once] [--every ] [--no-reply] [--yes] [instructions]…

QwenLM/qwen-code · 123 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openinterpreter/openinterpreter · 114 tokens

dsh-TUI: Skill for Claude Code