dx-agent-all

dx-agent-all is a skill for Claude Code from easingthemes/dx-aem-flow. It costs 45 tokens per session (9,101 once invoked), scanned B, original, MIT.

An end-to-end coordinator that takes an Azure DevOps work item from requirements through planning, coding, building, review, committing, and opening a pull request.

In plain words
What is it for?
Use it when you want to execute a complete development workflow for an Azure DevOps story identified by its work item ID.
Why use it?
It connects the stages of implementing a story so the work can proceed as one tracked run, with optional human checkpoints.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dx-core plugin — 49 skills, 7 agents shipped together

Good fit Use it when you want to execute a complete development workflow for an Azure DevOps story identified by its work item ID.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add easingthemes/dx-aem-flow
Claude Code
/plugin install dx-core

Made for: Claude Code.

Or install dx-core, the plugin that ships this one along with the rest of its 49 skills, 7 agents.

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 dx-agent-all

README.md
[![agentmods](https://agentmods.dev/badge/skills/easingthemes/dx-aem-flow/dx-agent-all.svg)](https://agentmods.dev/skills/easingthemes/dx-aem-flow/dx-agent-all)
Your own site
<a href="https://agentmods.dev/skills/easingthemes/dx-aem-flow/dx-agent-all"><img src="https://agentmods.dev/badge/skills/easingthemes/dx-aem-flow/dx-agent-all.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,101 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.09101
Opus 5 $0.00023 $0.04550
Sonnet 5 $0.00009 $0.01820
Haiku 4.5 $0.00005 $0.00910

Measured 8d ago against content hash 001af178192b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

dx-agent-all scanned grade B with 1 finding 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/no-source-reads.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

Check the plan-validate result. If FAIL, stop. If PASS (with or without warnings), continue to feature branch creation.
plugins/dx-core/skills/dx-agent-all/SKILL.md · 738 lines

How it starts

The opening of the file, as written. The whole thing — 738 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the top-level coordinator. You orchestrate the entire development pipeline from ADO story to pull request.

Argument

The argument is the ADO work item ID — a numeric value (e.g., 2435084).

If the user provides a full ADO URL, extract the numeric ID.

If no argument is provided, ask the user for the work item ID.

Run-State Management

Maintain run state in $SPEC_DIR/run-state.json:

{
  "skill": "dx-agent-all",
  "ticket": "<id>",
  "started": "<ISO-8601>",
  "last_phase_completed": 0,
  "total_phases": 0
}

On invocation:

  1. Check for existing $SPEC_DIR/run-state.json
  2. If exists and fresh (<2 hours) → ask: "Previous run found at phase {last_phase_completed}/{total_phases}. Resume or start fresh?"
  3. If stale → start fresh, delete old state
  4. If not exists → create new

During execution: Update after each phase. On completion: Delete run-state.json.

Orchestration Flag

In addition to run-state.json, write a marker file .ai/run-context/orchestrating.flag at startup. Forked sub-skills check this file to determine whether they're running under the orchestrator (compact ## Return only) or standalone (verbose summary + ## Return).

On invocation, after run-state.json is created:

mkdir -p .ai/run-context
touch .ai/run-context/orchestrating.flag

After each phase transition (alongside run-state.json update):

touch .ai/run-context/orchestrating.flag

This refreshes the mtime so a long-running pipeline doesn't trip the 2h staleness check inside forked skills.

On any terminal state — Final Summary, STOP, validation failure, build/review failure routes:

rm -f .ai/run-context/orchestrating.flag

The flag's existence (and freshness) is the signal that forked sub-skills (dx-req, dx-plan, dx-plan-validate, dx-plan-resolve, dx-pr-commit, dx-step-all) read to suppress their human-friendly summary output. See plugins/dx-core/shared/orchestration-check.md.

Read the full file on GitHub · 738 lines

Files

What ships with it

1 file beside SKILL.md 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. 8d ago First seen · 738 lines · 45 tokens per session scan B 001af178192b

Subscribe to this mod's changes

dx-agent-all is a skill published in the GitHub repository easingthemes/dx-aem-flow (6 stars, last pushed 6d ago), licensed MIT. It adds 45 tokens to every session and 9,101 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.