agentmods.dev

dh

dh is a plugin for Claude Code from Jamie-BitFlight/claude_skills. Its manifest loads nothing; the 53 skills, 28 agents it bundles cost 6,765 tokens per session together, scanned A, original, MIT.

A plugin that provides a structured, seven-stage development process for coding agents. It includes orchestration, planning, verification, testing, backlog work, and a way to involve a person when decisions need review.

In plain words
What is it for?
Use it to coordinate feature work, groom and plan backlog items, run verification and testing stages, and compose the process with language-specific tools.
Why use it?
It gives agent-led development a repeatable workflow and keeps process artifacts and human review points organised.

Plugin for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

not rated 65repo changed 2d ago A scan tokens not measured original MIT

Good fit Use it to coordinate feature work, groom and plan backlog items, run verification and testing stages, and compose the process with language-specific tools.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add Jamie-BitFlight/claude_skills/plugin install dh
View source ↗ Jamie-BitFlight/claude_skills
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/Jamie-BitFlight/claude_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.

agentmods badge for dh

README.md
[![agentmods](https://agentmods.dev/badge/plugins/jamie-bitflight/claude_skills/development-harness.svg)](https://agentmods.dev/plugins/jamie-bitflight/claude_skills/development-harness)
Your own site
<a href="https://agentmods.dev/plugins/jamie-bitflight/claude_skills/development-harness"><img src="https://agentmods.dev/badge/plugins/jamie-bitflight/claude_skills/development-harness.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 53 skills, 28 agents cost 6,765 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

dh 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/development-harness/.claude-plugin/plugin.json · 35 lines

What it actually says

{
  "name": "dh",
  "description": "Language-agnostic development process harness implementing the Stateless Agent Methodology (SAM) 7-stage pipeline with ARL human touchpoint model and Voltron-style language plugin composition. Provides orchestration, workflows, planning, verification, and testing methodology that any language plugin can compose with.",
  "version": "11.0.20",
  "author": {
    "name": "Jamie Nelson",
    "url": "https://github.com/bitflight-devops"
  },
  "mcpServers": {
    "backlog": {
      "command": "uv",
      "args": [
        "run",
        "--script",
        "${CLAUDE_PLUGIN_ROOT}/scripts/run_backlog_server.py"
      ]
    },
    "sam": {
      "command": "uv",
      "args": [
        "run",
        "--script",
        "${CLAUDE_PLUGIN_ROOT}/scripts/run_sam_server.py"
      ]
    },
    "sequential_thinking": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-sequential-thinking@latest"
      ]
    }
  }
}
Contents

What it installs

The manifest is a name and a version. 53 skills, 28 agents travel with it, and installing the plugin installs all of them — 6,765 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 2d ago Changed 979d31725def
  2. 3d ago Changed 782f5a1ba167
  3. 3d ago First seen · 35 lines scan A 10c2fb24cc51

Subscribe to this mod's changes

dh is a plugin published in the GitHub repository Jamie-BitFlight/claude_skills (65 stars, last pushed yesterday), 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.

Building agentsProject management
Related

Other plugins, from other repositories

before-you-build

Pre-build product risk review for founders, product teams, and AI-assisted builders before implementation starts.

wshobson/agents · not measured

obw

Obsidian Workspace — project-scoped vault productivity (capture / notes / PM). Skills-only: owns folder layout and templates; runs the Obsidian CLI directly via the official obsidian-cli skill.

musingfox/cc-plugins · not measured

mission-control

SDLC management for Operations, Asgard, and CAMPPS: prepared issue drafts, live schema sync, board schemas, labels, project fields, metrics, and card validation.

infiquetra/infiquetra-claude-plugins · not measured

feishu-calendar

Manage Feishu (Lark) calendar events — create, read, update, delete events and manage attendees via the Feishu Open Platform Calendar API v4.

ZW471/claude-feishu-calendar · not measured

gse

GSE-One — AI engineering companion for structured SDLC management. 24 commands, adaptive risk analysis, unified backlog, knowledge transfer, worktree isolation.

nicolasguelfi/gensem · not measured

product-management

Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.

fergupa/claude_plugins · not measured