agentmods.dev

cadence

cadence is a plugin for Claude Code from crenshawdev/cadence. Its manifest loads nothing; the 34 skills, 30 agents, 3 hooks it bundles cost 2,294 tokens per session together, scanned A, original, MIT.

A development workflow for one developer that separates planning, coding, and checking the result. It uses additional reviewers, including other AI models, to challenge plans and code changes.

In plain words
What is it for?
Use it to plan software changes, implement them, and have the plan and resulting code reviewed at defined checkpoints.
Why use it?
It helps expose mistakes or weak assumptions before work moves through the next stage, while keeping progress in files instead of the chat history.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest. Also seen: mentions subagents; mentions Claude Code.

not rated 8repo +2 changed 4d ago A scan tokens not measured original MIT

Good fit Use it to plan software changes, implement them, and have the plan and resulting code reviewed at defined checkpoints.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add crenshawdev/cadence
/plugin install cadence
View source ↗ crenshawdev/cadence
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.

Clone the repo
git clone --depth 1 https://github.com/crenshawdev/cadence

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.

agentmods badge for cadence

README.md
[![agentmods](https://agentmods.dev/badge/plugins/crenshawdev/cadence/cadence/github.svg)](https://agentmods.dev/plugins/crenshawdev/cadence/cadence)
Your own site
<a href="https://agentmods.dev/plugins/crenshawdev/cadence/cadence"><img src="https://agentmods.dev/badge/plugins/crenshawdev/cadence/cadence/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.

agentmods 80×15 button for cadence

Your own site · 80×15
<a href="https://agentmods.dev/plugins/crenshawdev/cadence/cadence"><img src="https://agentmods.dev/badge/plugins/crenshawdev/cadence/cadence.svg" alt="Reviewed on agentmods" width="80" 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 34 skills, 30 agents, 3 hooks cost 2,294 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

cadence 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 4d 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.

.claude-plugin/plugin.json · 20 lines

What it actually says

{
  "name": "cadence",
  "displayName": "Cadence",
  "description": "A plan/execute/verify loop for a single developer in Claude Code, with adversarial review at every gate: plans and diffs get refuted by a fresh Claude subagent or a panel of outside models (OpenAI, Gemini, DeepSeek), not just approved. State lives in files, not the conversation, so you clear aggressively and keep both your context and your token bill lean.",
  "version": "3.9.0",
  "author": {
    "name": "John Crenshaw"
  },
  "homepage": "https://github.com/crenshawdev/cadence",
  "repository": "https://github.com/crenshawdev/cadence.git",
  "license": "MIT",
  "keywords": [
    "planning",
    "workflow",
    "claude-code",
    "software-development",
    "git"
  ]
}
Contents

What it installs

The manifest is a name and a version. 34 skills, 30 agents, 3 hooks travel with it, and installing the plugin installs all of them — 2,294 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 plugin.json 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.

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. 4d ago Changed · -8 lines 928156df33de
  2. 10d ago Changed · +8 lines 57b163250717
  3. 11d ago Changed e781e28b434b
  4. 21d ago Changed 9d8e15dfdd2b
  5. 1mo ago Changed 47927960bf04
  6. 1mo ago Changed 665e70760135
  7. 1mo ago First seen · 20 lines scan A 6b2fea200f9c

Subscribe to this mod's changes

cadence is a plugin published in the GitHub repository crenshawdev/cadence (8 stars, last pushed 4d 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.

Building agentsClaude CodeCode reviewGit and workflowPlanningai-assisted-developmentclaude-code-pluginclaude-plugin
Related

Other plugins, from other repositories

han-github

Github specific extensions to the Han plugin for agentic planning and coding. Provides skills to post code reviews as PR comments, update a PR description with a consistent format, etc.

testdouble/han · not measured

gerrit

An MCP server for interacting with the Gerrit code review system.

GerritCodeReview/gerrit-mcp-server · not measured

odin-git

ODIN workflows for commits, branches, pull requests, review feedback, and issue tracking.

OutlineDriven/odin-claude-plugin · not measured

open-pr

Pre-flight checks and PR creation workflow: run tests, open a PR, code review, and check CI.

harnessprotocol/harness-kit · not measured

hope

Adds intent-and-decision alignment before implementation with an optional durable HTML record, explicit behavior-preserving codebase cleanup, evidence-based review and fixes repeated until material issues are resolved, PR explanations and a complete diff reader with reasons, UI design and mockups, clear explanatory…

dkstm95/hope · not measured

pr-trains

Batch operators for GitHub queues: review-train reviews every open PR, fix-train applies requested changes, fix-ci-train turns red CI green, merge-train fixes and merges in dependency order, issue-train triages and builds one PR per actionable issue — all with parallel sub-agents and one grouped confirmation.

big-emotion/agent-atelier · not measured