FinishDev

FinishDev is a command for Claude Code from Evyasys-Software-Solutions/EvyaGovernance. It costs 34 tokens per session (560 once invoked), scanned A, original, MIT.

A development wrap-up command that checks acceptance-criteria coverage, the definition of done, and the size of the code changes before QA.

In plain words
What is it for?
Use it to review a story’s implementation, match each acceptance criterion to a test, summarize the development work, and move the item to Ready for QA.
Why use it?
It exposes missing tests, unresolved requirements, or unrelated changes before work is handed to testing.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the evyasys plugin — 15 skills, 15 commands 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 commands/evyasys-software-solutions/evyagovernance/finishdev
Clone the repo
git clone --depth 1 https://github.com/Evyasys-Software-Solutions/EvyaGovernance

Made for: Claude Code.

Or install evyasys, the plugin that ships this one along with the rest of its 15 skills, 15 commands.

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 FinishDev

README.md
[![agentmods](https://agentmods.dev/badge/commands/evyasys-software-solutions/evyagovernance/finishdev.svg)](https://agentmods.dev/commands/evyasys-software-solutions/evyagovernance/finishdev)
Your own site
<a href="https://agentmods.dev/commands/evyasys-software-solutions/evyagovernance/finishdev"><img src="https://agentmods.dev/badge/commands/evyasys-software-solutions/evyagovernance/finishdev.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 560 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00034 $0.00560
Opus 5 $0.00017 $0.00280
Sonnet 5 $0.00007 $0.00112
Haiku 4.5 $0.00003 $0.00056

Measured 5d ago against content hash 522c175b332d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

FinishDev scanned grade A with 1 finding 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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

macOS / Linux (Bash): `EVYA_AI=$(find "$HOME/.claude/plugins" -maxdepth 6 -type d -name ".ai" 2>/dev/null | grep -i "EvyaGovernance" | head -1); [ -z "$EVYA_AI" ] && EVYA_AI=".ai"; echo "$EVYA_AI"`

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

commands/FinishDev.md · 25 lines

What it actually says

You are running /evyasys:FinishDev $ARGUMENTS.

If $ARGUMENTS is empty, ask for the StoryID.

  1. Find the plugin's installed workflow directory, then load all files under <plugin-ai>/workflows/finish-dev/ (+ project overrides). If any file is not found at the plugin path, fall back to the same filename under .ai/workflows/finish-dev/. Read story, subtasks, brainstorm.

    macOS / Linux (Bash): EVYA_AI=$(find "$HOME/.claude/plugins" -maxdepth 6 -type d -name ".ai" 2>/dev/null | grep -i "EvyaGovernance" | head -1); [ -z "$EVYA_AI" ] && EVYA_AI=".ai"; echo "$EVYA_AI"

    Windows (PowerShell): $EVYA_AI = (Get-ChildItem "$env:USERPROFILE\.claude\plugins" -Recurse -Directory -Filter ".ai" -ErrorAction SilentlyContinue | Where-Object { $_.FullName -like '*EvyaGovernance*' } | Select-Object -First 1 -ExpandProperty FullName); if (-not $EVYA_AI) { $EVYA_AI = ".ai" }; Write-Output $EVYA_AI

  2. Run git diff main...HEAD and python scripts/repo_scan.py --story $ARGUMENTS --diff.

  3. For every AC: find the test (file + test name). For any uncovered AC, follow QUESTIONING.md — ask one question at a time. Do NOT proceed with any ❌ unresolved.

  4. Self-review against CHECKLIST.md. Every mandatory item must pass.

  5. For any diff anomaly (files outside scope, debug code, missing migrations), ask one question at a time per QUESTIONING.md.

  6. Produce Dev Summary using PROMPT.md structure. Show to user and wait for approval.

  7. On approval → save <StoryID>_DevSummary.md to story folder → ADO Ready for QA → Teams handoff card.

Output: Dev Summary path · ADO 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.

  1. 5d ago First seen · 25 lines · 34 tokens per session scan A 522c175b332d

Subscribe to this mod's changes

FinishDev is a command published in the GitHub repository Evyasys-Software-Solutions/EvyaGovernance (7 stars, last pushed 24d ago), licensed MIT. It adds 34 tokens to every session and 560 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.