devtools

A command set for launching Claude DevTools, a desktop app for inspecting coding-agent work, and viewing its session dashboard.

In plain words
What is it for?
Use it to start or focus Claude DevTools and inspect agent sessions, dispatched work, evaluation convergence, spending, and hot files.
Why use it?
It gives you one place to check whether DevTools is installed or running and review agent activity, costs, evaluation progress, and frequently changed files.

Command for Claude Code

Part of the productionos plugin — 4 skills, 41 commands, 11 agents shipped together

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/shaheerkhawaja/productionos/devtools
Clone the repo
git clone --depth 1 https://github.com/ShaheerKhawaja/ProductionOS

Made for: Claude Code.

Or install productionos, the plugin that ships this one along with the rest of its 4 skills, 41 commands, 11 agents.

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 729 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 $0.00032 $0.00729
Opus 5 $0.00016 $0.00365
Sonnet 5 $0.00006 $0.00146
Haiku 4.5 $0.00003 $0.00073

Measured 3d ago against content hash 5665b00c6280, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devtools 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 3d 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/commands/devtools.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ProductionOS DevTools — Mission Control

Step 0: Preamble

Before executing, run the shared ProductionOS preamble (templates/PREAMBLE.md) to confirm the active install root and session context.

Execute the requested action for Claude DevTools within the ProductionOS ecosystem.

Action: $ARGUMENTS.action

Step 1: Check DevTools installation and status

DEVTOOLS_APP="/Applications/claude-devtools.app"
if [ ! -d "$DEVTOOLS_APP" ]; then
  echo "DEVTOOLS_NOT_INSTALLED"
  echo "Install with: brew install --cask claude-devtools"
else
  DEVTOOLS_PID=$(pgrep -f "claude-devtools" 2>/dev/null | head -1)
  if [ -n "$DEVTOOLS_PID" ]; then
    echo "DEVTOOLS_RUNNING (PID: $DEVTOOLS_PID)"
  else
    echo "DEVTOOLS_STOPPED"
  fi
fi

If not installed, tell the user to run brew install --cask claude-devtools and stop.

Step 2: Execute action

launch (default):

  1. If DevTools is NOT running, launch it:
    open /Applications/claude-devtools.app
    
  2. If already running, bring to foreground:
    osascript -e 'tell application "claude-devtools" to activate'
    
  3. Then show the full dashboard (Step 3)

status:

  1. Run the dashboard script for the full report:
    python3 "${CLAUDE_PLUGIN_ROOT:-$HOME/.claude/plugins/marketplaces/productionos}/hooks/devtools-dashboard.py" --full
    
  2. Display the output to the user as-is (it's already formatted)

focus:

  1. Bring DevTools window to foreground:
    osascript -e 'tell application "claude-devtools" to activate'
    

quit:

  1. Gracefully quit DevTools:
    osascript -e 'tell application "claude-devtools" to quit'
    

Step 3: Full Dashboard (runs on launch and status)

Run the dashboard script:

python3 "${CLAUDE_PLUGIN_ROOT:-$HOME/.claude/plugins/marketplaces/productionos}/hooks/devtools-dashboard.py" --full

This shows:

  • Session metrics (edits, agents, security events)
  • Cost tracking (session delta, all-time total)
  • Eval convergence (latest score, sparkline trend, data points)
  • Agent dispatch breakdown by type
  • Hot files (cross-session churn with bar charts)
  • Event breakdown

Read the full file on GitHub · 94 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. 3d ago First seen · 94 lines · 32 tokens per session scan A 5665b00c6280

Subscribe to this mod's changes

devtools is a command published in the GitHub repository ShaheerKhawaja/ProductionOS (8 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 729 once invoked, about $0.0002 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 2026-08-31.