smith-finish

smith-finish is a skill for Claude Code, Codex from ATTCKDigital/smith. It costs 26 tokens per session (2,175 once invoked), scanned A, original, MIT.

An end-of-session workflow for finishing software work by checking the repository, committing and pushing changes, merging them into the main branch, updating specifications, and cleaning the workspace.

In plain words
What is it for?
Use it when you are done working and want to close out the session. It checks the current branch, changes, commits, pull requests, and configured base branch before completing the workflow.
Why use it?
It helps prevent unfinished or uncommitted work from being left behind when a coding session ends.

Skill for Claude CodeCodex

Part of the smith plugin — 32 skills, 7 agents shipped together

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/attckdigital/smith/smith-finish
Any agent
npx skills add ATTCKDigital/smith --skill smith-finish
Clone the repo
git clone --depth 1 https://github.com/ATTCKDigital/smith

Made for: Claude Code, Codex.

Or install smith, the plugin that ships this one along with the rest of its 32 skills, 7 agents.

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 smith-finish

README.md
[![agentmods](https://agentmods.dev/badge/skills/attckdigital/smith/smith-finish.svg)](https://agentmods.dev/skills/attckdigital/smith/smith-finish)
Your own site
<a href="https://agentmods.dev/skills/attckdigital/smith/smith-finish"><img src="https://agentmods.dev/badge/skills/attckdigital/smith/smith-finish.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,175 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 $0.00026 $0.02175
Opus 5 $0.00013 $0.01087
Sonnet 5 $0.00005 $0.00435
Haiku 4.5 $0.00003 $0.00217

Measured 4d ago against content hash c296f7046974, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

smith-finish 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 4d 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.

skills/smith-finish/SKILL.md · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Smith — Session Finish

Skill Purpose

End-of-session workflow that ensures all work is committed, pushed, merged to main, specs are updated, and the workspace is clean. Prevents losing work when closing a development session.

When to Use

  • User is done working and wants to wrap up
  • User wants to ensure nothing is lost before ending a session
  • Triggered by /smith-finish

How to Execute

Run all steps autonomously. Only stop to ask the user if a decision is genuinely ambiguous (e.g., unrelated uncommitted changes that may need separate branches).


Step 1: Inventory — Assess Current State

Gather all of the following in parallel:

# Resolve the configured base branch (falls back to main when unconfigured)
BASE_BRANCH=$(.specify/scripts/bash/get-base-branch.sh)

# What branch are we on?
git rev-parse --abbrev-ref HEAD

# Any uncommitted changes?
git status

# Any unpushed commits? (only if on a branch other than the base branch)
git log origin/$(git rev-parse --abbrev-ref HEAD)..HEAD --oneline 2>/dev/null

# What files changed vs the configured base branch?
git diff "$BASE_BRANCH" --name-only 2>/dev/null

# Any open PRs for this branch?
gh pr list --head $(git rev-parse --abbrev-ref HEAD) --state open --json number,title,url 2>/dev/null

Present a brief status summary to the user:

Session Status:
- Branch: <branch-name>
- Uncommitted changes: <count> files
- Unpushed commits: <count>
- Open PRs: <count>
- Files changed vs main: <count>

Decision tree based on state:

State Action
On main, no changes Nothing to do. Report "workspace is clean" and exit.
On main, uncommitted changes Create a feature branch (fix/<slug> or feat/<slug> based on changes), then continue to Step 2. Ask the user for a brief description to name the branch.
On feature branch, uncommitted changes Continue to Step 2.
On feature branch, all committed + pushed + PR merged Skip to Step 6 (verify clean state).
On feature branch, all committed + pushed + PR open Skip to Step 4 (spec updates, then merge).
On feature branch, all committed + not pushed Skip to Step 3 (push).

Read the full file on GitHub · 281 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. 4d ago First seen · 281 lines · 26 tokens per session scan A c296f7046974

Subscribe to this mod's changes

smith-finish is a skill published in the GitHub repository ATTCKDigital/smith (52 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 2,175 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.