A final quality check for code changes before committing them to version control. It cleans up the working changes, runs the project's configured tests, and reports the results.

Use it at the end of a coding task to review changed and new files, apply selected cleanup edits, and rerun the project's test command.

It catches avoidable quality issues and test failures before changes are recorded or shared.

dev-quality — Skill by gtapps

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/gtapps/claude-code-hermit/dev-quality

Any agent

npx skills add gtapps/claude-code-hermit --skill dev-quality

Clone the repo

git clone --depth 1 https://github.com/gtapps/claude-code-hermit

Made for: Claude Code, Codex.

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,346 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.

Model	Per session	Once invoked
Fable 5	$0.00058	$0.02346
Opus 5	$0.00029	$0.01173
Sonnet 5	$0.00012	$0.00469
Haiku 4.5	$0.00006	$0.00235

Measured 2d ago against content hash ef0705d3de8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-quality 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 2d 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.

plugins/claude-code-dev-hermit/skills/dev-quality/SKILL.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/dev-quality

Run a cleanup pass on the working-tree changes before declaring the task done. Invokes /claude-code-hermit:simplify — three parallel reviewers (reuse, quality, efficiency) propose edits; the skill applies the edits it picks (per its Principles) and reports totals. Then re-runs the configured test command. Call this at task wrap-up, before committing.

Prerequisites

Verify .claude-code-hermit/sessions/ exists. If not: tell the operator to run /claude-code-hermit:hatch and /claude-code-dev-hermit:hatch first.
Read .claude-code-hermit/config.json once. Cache commands.test (if unset, the test step is skipped — /claude-code-hermit:simplify still runs) and claude-code-dev-hermit.protected_branches (default ["main", "master"] if absent).

Plan

Argument

Optional --cwd <path>. When set, all git operations and the test re-run target <path> instead of $PWD. <path> must be a git working tree. Use this for nested-repo workflows (see CLAUDE-APPEND §Implementation Flow). State (last-test.json, hermit dir) still resolves from $PWD.

In the gates below, use git -C "<path>" for every git invocation when --cwd is set, otherwise omit the -C and run against $PWD as today. Below this is written as git -C "$TARGET" with $TARGET standing for either form.

Gate 0 — preconditions

git -C "$TARGET" status --porcelain

Empty output → working tree is clean (no modified, staged, or untracked-but-not-ignored files). Any non-empty output passes Gate 0, including untracked-only changes — /claude-code-hermit:simplify captures new files via git status --short + synthetic +++ blocks, so a task that only adds files still has cleanup scope.

Before failing on empty output, run the following checks in order:

Resolve BASE_NAME using the same priority order as /dev-pr Gate 0 step 4 (pr_base_branch → first non-glob protected_branches → origin/HEAD → main/master).
Resolve BASE_REF: try git -C "$TARGET" rev-parse --verify "$BASE_NAME" 2>/dev/null; on failure try git -C "$TARGET" rev-parse --verify "origin/$BASE_NAME" 2>/dev/null; if neither resolves, skip the NOTICE.
If git -C "$TARGET" rev-list --count "$BASE_REF..HEAD" > 0, emit before failing:

Read the full file on GitHub · 186 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.

2d ago First seen · 186 lines · 58 tokens per session scan A ef0705d3de8f

Subscribe to this mod's changes

dev-quality is a skill published in the GitHub repository gtapps/claude-code-hermit (73 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 2,346 once invoked, about $0.0003 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.

Code review Testing ai ai-agent anthropic claude claude-code claude-code-plugin

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens