A session-completion workflow that reviews the work, archives the session, creates a report, and commits the changes. A session is a defined period of project work with tracked files and a plan.

Use it when you are ready to finish a coding session. It checks changed files, runs the project's tests, audits the plan, archives the session, writes a report, and commits the result.

It puts the final checks and record-keeping in one sequence, while stopping if review or tests find a blocking problem.

How g-hyeong/MCP-AidFlow configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to g-hyeong/MCP-AidFlow. 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/g-hyeong/MCP-AidFlow/main/.claude/skills/finish/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/g-hyeong/MCP-AidFlow

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/g-hyeong/mcp-aidflow/finish/github.svg)](https://agentmods.dev/skills/g-hyeong/mcp-aidflow/finish)

Your own site

<a href="https://agentmods.dev/skills/g-hyeong/mcp-aidflow/finish"><img src="https://agentmods.dev/badge/skills/g-hyeong/mcp-aidflow/finish/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/g-hyeong/mcp-aidflow/finish"><img src="https://agentmods.dev/badge/skills/g-hyeong/mcp-aidflow/finish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 943 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	$0.00017	$0.00943
Opus 5.5	$0.00007	$0.00377
Sonnet 5.5	$0.00003	$0.00189
Haiku 4.5	$0.00002	$0.00094

Measured 2mo ago against content hash 34b30467dffd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 2mo 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/skills/finish/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Complete the current session by running review, archive, report, and commit sequentially. Stop immediately at any step if a blocking issue is found.

Step 1: Review

Identify the active session
- Use session status to find the current session and its changed files
- Read plan.md to understand what was intended
Code Review - Changed Files Read EVERY changed file and check:
- Does the implementation match plan.md requirements?
- Are there any incomplete TODOs or FIXMEs?
- Error handling: are edge cases covered?
- If SPEC.md exists, do changes follow its conventions?
- Are there any hardcoded values that should be configurable?
- Security: no exposed secrets, no injection vulnerabilities?
Consistency Check
- Naming conventions consistent across new/modified code?
- Import patterns match existing codebase style?
- No duplicate logic that should be extracted?
- No dead code or unused imports left behind?
Test Coverage
- Run existing tests: npm test (or project-specific command from SPEC.md)
- If tests fail, STOP here and report failures to the user
Plan Completion Audit
- Check each Implementation Item and Acceptance Criteria in plan.md
- Ensure all - [ ] items are checked - [x] if completed
- Flag any genuinely unchecked items
Review Gate
- If blocking issues found: present them with AskUserQuestion, offer "Fix now" / "Proceed anyway" / "Cancel"
- If "Fix now": fix issues, then restart from Step 1
- If "Cancel": stop entirely
- If no issues or "Proceed anyway": continue to Step 2

Step 2: Archive Session

Run session complete to archive the session.

If it fails due to incomplete plan items, use force: true

Step 3: Generate Report

Find the latest directory in .aidflow/history/ (sorted by name, newest first)
Read meta.json from that directory to get session metadata
Read plan.md from that directory (if exists)
Gather git commits for the session period:
- Use created_at and completed_at from meta.json as the time range
- Run: git log --oneline --after="{created_at}" --before="{completed_at}"
Read the changed files listed in meta.json and briefly review each
Write report.md in the history directory with this format:

Read the full file on GitHub · 112 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.

2mo ago First seen · 112 lines · 17 tokens per session scan A 34b30467dffd

Subscribe to this mod's changes

finish is a skill published in the GitHub repository g-hyeong/MCP-AidFlow (0 stars, last pushed 8mo ago), licensed MIT. It adds 17 tokens to every session and 943 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 2026-08-31.

Git and workflow

finish next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
finishg-hyeong/MCP-AidFlow	Skill	0	8mo ago	MIT	A	17	Claude Code
merge-batchdiegosouzapw/OmniRoute	Skill	83k	6d ago	MIT	A	46	Claude Code
prowler-commitprowler-cloud/prowler	Skill	15k	today	Apache-2.0	A	44	Claude Code, Codex
gh-auth-isolationgithub/gh-aw	Skill	5.6k	yesterday	MIT	A	20	Claude Code, Codex
github-skillzeenie-ai/OpenCompany	Skill	1.1k	2d ago	MIT	A	51	Claude Code
comet-githubrpamis/comet	Skill	3.3k	yesterday	MIT	A	72	Claude Code, Codex
release-helperSahir619/fable-method	Skill	2.3k	1mo ago	MIT	A	43	Claude Code

MCP-AidFlow: Skill for Claude Code