What is workflow-skills?

A collection of coding workflows for handling issues, tests, continuous integration (automated checks), pull requests, documentation, and code cleanup.

Use it to triage issues, apply test-driven development (writing tests before code), fix failing CI, review pull requests, remove dead code, audit visual output, and prepare or close development sessions.

It gives recurring maintenance tasks a consistent process and helps developers check changes with evidence instead of guesswork.

workflow-skills — Plugin for Claude Code by jerseycheese: A collection of coding workflows for handling issues, tests…

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.

Claude Code

/plugin marketplace add jerseycheese/agent-skills

agentmods

npx agentmods add plugins/jerseycheese/agent-skills/workflow-skills

Clone the repo

git clone --depth 1 https://github.com/jerseycheese/agent-skills

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/plugins/jerseycheese/agent-skills/workflow-skills.svg)](https://agentmods.dev/plugins/jerseycheese/agent-skills/workflow-skills)

Your own site

<a href="https://agentmods.dev/plugins/jerseycheese/agent-skills/workflow-skills"><img src="https://agentmods.dev/badge/plugins/jerseycheese/agent-skills/workflow-skills.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 31 skills cost 3,670 tokens a session between them.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

workflow-skills 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 yesterday.

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-plugin/marketplace.json#workflow-skills · 49 lines

What it actually says

{
  "name": "workflow-skills",
  "source": "./",
  "description": "Issue triage, TDD, CI fix-with-memory, design-system guard, PR review, dead-code and doc-rot cleanup, comment and test reaping, code-health and visual-QA audits, evidence-checked claims, worktree setup, project bootstrap, cross-provider skill parity, and session wrap-up skills.",
  "strict": false,
  "keywords": [
    "workflow",
    "skills",
    "testing",
    "code-review",
    "issue-triage",
    "documentation",
    "visual-qa"
  ],
  "license": "MIT",
  "skills": [
    "./skills/abstraction-finder",
    "./skills/analyze-issue",
    "./skills/band-aid-finder",
    "./skills/browser-debugger-cli",
    "./skills/ci-fix-with-memory",
    "./skills/code-health-audit",
    "./skills/comment-reaper",
    "./skills/cyoa",
    "./skills/dead-code-cleanup",
    "./skills/doc-rot",
    "./skills/drupal-mental-model",
    "./skills/ds-guard",
    "./skills/evidence-check",
    "./skills/github-screenshot",
    "./skills/issue-maintenance",
    "./skills/kiss",
    "./skills/plain-language-audit",
    "./skills/post-merge",
    "./skills/pr-review-fix-pipeline",
    "./skills/prioritize-issues",
    "./skills/project-bootstrap",
    "./skills/ship-issue",
    "./skills/skill-parity",
    "./skills/tdd-implement",
    "./skills/test-fix",
    "./skills/test-reaper",
    "./skills/test-workflow",
    "./skills/visual-crawl",
    "./skills/visual-qa-pipeline",
    "./skills/worktree-enhanced",
    "./skills/wrap-it-up"
  ]
}

Contents

What it installs

The manifest is a name and a version. 31 skills travel with it, and installing the plugin installs all of them — 3,670 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside marketplace.json#workflow-skills in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

marketplace.json 1.9 KB

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.

yesterday First seen · 49 lines scan A a833fc1a8565

Subscribe to this mod's changes

workflow-skills is a plugin published in the GitHub repository jerseycheese/agent-skills (1 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.

Code review TDD Testing agent-skills ai-tools claude-code codex developer-tools gemini-cli

implementation

Disciplined implementation stage: execute approved plans inline (/implementation:implement) or via orchestrated worker subagents (/implementation:implement-dispatch) with incremental validation, TDD-by-default cadence, green-checkpoint commits, scope-fence drift detection, and divergence detection that routes back.

melodic-software/claude-code-plugins · not measured

mutation-testing

Measures whether a test suite can actually detect faults, not merely execute code: /mutation-testing:principles answers operator, mutant-state, and metric questions from the primary literature; /mutation-testing:setup verifies the ecosystem's mutation tool and writes the tracked config; /mutation-testing:audit ru.

melodic-software/claude-code-plugins · not measured

workflow-skills