finish-issue

finish-issue is a command for Claude Code from epam/ai-dial-core. It costs 15 tokens per session (304 once invoked), scanned A, original, Apache-2.0.

A command that runs style checks and the complete test suite, then commits work for a GitHub issue on the current issue branch. It stages only files related to that issue and uses a conventional commit message.

In plain words
What is it for?
Use it to finish an issue started with /start-issue, after the implementation is ready; pushing and opening a pull request are separate steps.
Why use it?
It catches code-quality problems and regressions before committing. It also prevents unrelated files from being included in the commit.

Command for Claude Code

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 commands/epam/ai-dial-core/finish-issue
Clone the repo
git clone --depth 1 https://github.com/epam/ai-dial-core

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 finish-issue

README.md
[![agentmods](https://agentmods.dev/badge/commands/epam/ai-dial-core/finish-issue.svg)](https://agentmods.dev/commands/epam/ai-dial-core/finish-issue)
Your own site
<a href="https://agentmods.dev/commands/epam/ai-dial-core/finish-issue"><img src="https://agentmods.dev/badge/commands/epam/ai-dial-core/finish-issue.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 304 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 5.1 $0.00015 $0.00304
Opus 5 $0.00008 $0.00152
Sonnet 5 $0.00003 $0.00061
Haiku 4.5 $0.00002 $0.00030

Measured 5d ago against content hash 2afd63670e0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

finish-issue 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 5d 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.

.claude/commands/finish-issue.md · 28 lines

What it actually says

Finish a GitHub issue (checks + commit)

Run on the issue branch created by /start-issue. Derive the issue number and commit type from the branch name (e.g., fix/issue-1234 → type fix, issue 1234).

Steps

  1. Run checkstyle and the full test suite to catch any cross-module regressions:

    ./gradlew checkstyleMain checkstyleTest
    ./gradlew test
    

    If any check or test fails, stop. Investigate and fix the failures before staging or committing.

  2. Stage only the files related to this issue. Do not commit unrelated files (local configs, IDE files, etc.). Inspect git status before staging.

  3. Commit using conventional commit format:

    {type}: {description} #{issue_number}
    
    • {type} matches the branch prefix (fix / feat / chore).
    • {description} is derived from the GitHub issue title; refine only if needed for clarity or to fit the line length.

After the commit, stop and wait for the user. Use /open-pr to push and open a PR when ready.

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. 5d ago First seen · 28 lines · 15 tokens per session scan A 2afd63670e0c

Subscribe to this mod's changes

finish-issue is a command published in the GitHub repository epam/ai-dial-core (658 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 304 once invoked, about $0.0001 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 2026-08-30.