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/juanmhidalgo/claude-pluginsWrote 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/juanmhidalgo/claude-plugins/feature-dev)<a href="https://agentmods.dev/plugins/juanmhidalgo/claude-plugins/feature-dev"><img src="https://agentmods.dev/badge/plugins/juanmhidalgo/claude-plugins/feature-dev/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/juanmhidalgo/claude-plugins/feature-dev"><img src="https://agentmods.dev/badge/plugins/juanmhidalgo/claude-plugins/feature-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
feature-dev 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.
What it actually says
{
"name": "feature-dev",
"description": "Feature development workflows: spec-driven development, test-driven development with coverage gates, and parallel codebase exploration",
"version": "2.1.2",
"types": "./types/index.d.ts",
"userConfig": {
"review_band": {
"type": "boolean",
"title": "Review band",
"description": "Show the band above the prompt that lists specs and plans changed since their last browser review",
"default": true
},
"spec_store": {
"type": "string",
"title": "Spec store",
"description": "Where approved specs live by default: the local file only, or also a GitHub issue. spec_store in .claude/feature-dev.local.md overrides it per project",
"options": ["file", "issue"],
"default": "file"
}
},
"author": {
"name": "Juan M. Hidalgo"
}
}
What it installs
The manifest is a name and a version. 2 skills, 7 commands, 13 agents travel with it, and installing the plugin installs all of them — 2,126 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill spec-driven-development A 48 tokens
- Skill tdd-patterns A 35 tokens
- Command tdd A 35 tokens
- Command explore-plan A 36 tokens
- Command cleanup A 80 tokens
- Command spec A 29 tokens
- Command review A 68 tokens
- Command spec-review A 39 tokens
- Command plan-review A 72 tokens
- Agent spec-plan-validator A 105 tokens
- Agent cross-repo-advisor A 350 tokens
- Agent api-contract-explorer A 58 tokens
- Agent observability-explorer A 36 tokens
- Agent schema-explorer A 42 tokens
- Agent config-explorer A 42 tokens
- Agent history-explorer A 35 tokens
- Agent test-explorer A 36 tokens
- Agent backend-explorer A 37 tokens
- Agent frontend-explorer A 38 tokens
- Agent tdd-runner A 350 tokens
- Agent feature-implementer A 298 tokens
- Agent plan-step-executor A 257 tokens
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 Changed · -13 lines 8c0f6f337c59
- 10d ago Changed a2006d140ea9
- 14d ago Changed · +29 lines fb4f1ade2f3a
- 17d ago Changed 00b6af6d8e67
- 18d ago Changed fe09521f548e
- 19d ago Changed 1fc7d157346f
- 23d ago Changed 61d67588068f
- 29d ago Changed a5649510f31d
- 1mo ago Changed 94dac4391aec
- 1mo ago First seen · 9 lines scan A 7919fa26ae5a
feature-dev is a plugin published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 2d 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
jira-pack
Issue-tracker pack: /jira-fix takes a ticket link of any type, verifies tracker access, classifies it as a defect or a change, reproduces the defect or writes a failing acceptance test for the change, routes the work to core executors, comments back with evidence and moves the ticket to the QA column. Opt-in; requires.
whetstone
Engineering-craft skills: red-green TDD, flaky-test audit, diagnosis, doubt review, grilling, merge-conflict resolution, research reports with grounded claims, HTML reports, skill linting and a column budget. Every gate among them carries a deterministic self-verify.
es6kr
A collection of AI coding skills including TDD, commit management, dotfile sync, and more.
superpowers-deepseek-v4
Superpowers DeepSeek v4: composable agent skills for TDD, debugging, and collaboration. Independently maintained; not identical to obra/superpowers.
knowledge-virtuoso
15 knowledge skills — design patterns, refactoring, SOLID, debugging, clean architecture, testing, API design, security, scrum, performance, microservices, git workflow, CI/CD, accessibility, and database design.
safeword
AI coding agent workflows: BDD, auto-linting, quality reviews, debugging, and refactoring. Run safeword install in a project to enroll it.