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.
git clone --depth 1 https://github.com/refo/claude-dev-helpersWrote 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.
[](https://agentmods.dev/plugins/refo/claude-dev-helpers/dev-helpers)<a href="https://agentmods.dev/plugins/refo/claude-dev-helpers/dev-helpers"><img src="https://agentmods.dev/badge/plugins/refo/claude-dev-helpers/dev-helpers/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.
<a href="https://agentmods.dev/plugins/refo/claude-dev-helpers/dev-helpers"><img src="https://agentmods.dev/badge/plugins/refo/claude-dev-helpers/dev-helpers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
dev-helpers 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 1mo 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.
What it actually says
{
"name": "dev-helpers",
"version": "0.1.1",
"description": "Stack-agnostic agentic dev workflow helpers: TDD, commits, PRDs, issue triage, pre-commit setup, design grilling. Reads per-project config from .claude/helpers.json.",
"author": {
"name": "Refik Önal"
},
"keywords": ["tdd", "commit", "prd", "workflow", "git"],
"commands": "./commands"
}
What it installs
The manifest is a name and a version. 13 commands, 1 hook travel with it, and installing the plugin installs all of them — 269 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Command ubiquitous-language A 0 tokens
- Command design-an-interface A 0 tokens
- Command triage-issue A 0 tokens
- Command grill-me A 0 tokens
- Command prd-to-plan A 0 tokens
- Command write-a-prd A 51 tokens
- Command prd-to-issues A 50 tokens
- Command tdd B 45 tokens
- Command setup-pre-commit B 42 tokens
- Command commit B 11 tokens
- Command git-guardrails-claude-code B 0 tokens
- Command init-helpers C 41 tokens
- Command next-issue C 29 tokens
- Hook PreToolUse A not measured
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.
- 1mo ago First seen · 11 lines scan A 8aff7ac5774c
dev-helpers is a plugin published in the GitHub repository refo/claude-dev-helpers (2 stars, last pushed 3mo 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 2026-08-31.
Other plugins, from other repositories
es6kr
A collection of AI coding skills including TDD, commit management, dotfile sync, and more.
es6kr
Reusable AI coding skills: TDD, commit management, dotfile sync, and more.
engineering-practices
Git commits, conventional releases, refactoring, test-driven development, and engineering ways of working skills.
quatico-skills
Quatico development essentials: commit conventions, PR workflows, TDD, testing, Bitbucket/Jira integration, and team standards.
otter-skills
Portable software-craft skills for thin delivery, TDD, safe change, naming, refactoring, and trustworthy commits.
flow
Skill-driven workflow plugin for GitHub development with excellence-by-default quality gates. Encodes team knowledge as composable skills, enforces safety through hooks, and compounds learning across sessions. Strict TDD, Stranger Test, holdout validation, and evidence-based verification built in. Durable goals…