develop

A command for managing software changes through separate design, planning, coding, and review stages, using multiple AI models and agents.

In plain words
What is it for?
Use it to coordinate feature design, implementation, reviews, fixes, and repeated validation across several AI agents.
Why use it?
It organizes a full development cycle and adds review checkpoints, so work is less likely to skip planning or quality checks. It also records model results to help compare them later.

Command

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.

agentmods
npx agentmods add commands/madappgang/claude-code/develop
Clone the repo
git clone --depth 1 https://github.com/MadAppGang/claude-code
Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,762 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00070 $0.04762
Opus 5 $0.00035 $0.02381
Sonnet 5 $0.00014 $0.00952
Haiku 4.5 $0.00007 $0.00476

Measured yesterday against content hash d26f94927926, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

develop 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 yesterday.

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/agentdev/commands/develop.md · 515 lines

How it starts

The opening of the file, as written. The whole thing — 515 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Includes multi-model validation with parallel execution and quality gates.

<user_request> $ARGUMENTS </user_request>

  **You MUST:**
  - Use Task tool to delegate ALL work to agents
  - Use Tasks to track workflow
  - Use AskUserQuestion for approval gates
  - Coordinate multi-agent workflows

  **You MUST NOT:**
  - Write or edit ANY agent/command files directly
  - Design or implement features yourself
  - Skip delegation to agents
</orchestrator_role>

<delegation_rules>
  - ALL design → `agentdev:architect`
  - ALL implementation → `agentdev:developer`
  - ALL reviews → `agentdev:reviewer`
  - ALL fixes → `agentdev:developer`
</delegation_rules>

</critical_constraints>

      # Create directory structure
      mkdir -p "${SESSION_PATH}/reviews/plan-review" \
               "${SESSION_PATH}/reviews/impl-review" || {
        echo "Warning: Cannot create session directory, using legacy mode"
        SESSION_PATH="ai-docs"
      }

      # Create session metadata (if not legacy mode)
      if [[ "$SESSION_PATH" != "ai-docs" ]]; then
        cat > "${SESSION_PATH}/session-meta.json" << EOF
      {
        "session_id": "${SESSION_BASE}",
        "type": "agentdev",
        "target": "${USER_REQUEST}",
        "started_at": "$(date -u +%Y-%m-%dT%H:%M:%SZ)",
        "status": "in_progress"
      }
      EOF
      fi
      ```
      Store SESSION_PATH for all subsequent phases.
    </step>
    <step>
      **Debug Mode Check** (reads from .claude/agentdev-debug.json):
      ```bash
      DEBUG_ENABLED=false
      DEBUG_LEVEL="standard"
      if [ -f ".claude/agentdev-debug.json" ]; then
        if command -v jq &> /dev/null; then
          DEBUG_ENABLED=$(jq -r '.enabled // false' .claude/agentdev-debug.json)
          DEBUG_LEVEL=$(jq -r '.level // "standard"' .claude/agentdev-debug.json)
        fi
      fi
      if [ "$DEBUG_ENABLED" = "true" ]; then
        echo "Debug mode: ENABLED (level: $DEBUG_LEVEL)"
      fi
      ```
    </step>
  </steps>
  <quality_gate>Session initialized (SESSION_PATH set), Claudish checked</quality_gate>
</phase>

Read the full file on GitHub · 515 lines

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. yesterday First seen · 515 lines · 70 tokens per session scan A d26f94927926

Subscribe to this mod's changes

develop is a command published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 70 tokens to every session and 4,762 once invoked, about $0.0003 per session on Opus 5. 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 2026-08-30.