A command that starts an investigation on the hosted Production Master service and shows live progress in the editor. The investigation itself runs on the service, not on your computer.

Use it to send an investigation request, monitor its progress, read the report, and relay approval or rejection decisions.

It gives you a way to submit an investigation and follow its results without running the analysis locally.

investigate — Command for Claude Code by ProductionMasterAI

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/ProductionMasterAI/production-master

Made for: Claude Code.

Or install production-master, the plugin that ships this one along with the rest of its 4 commands.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/productionmasterai/production-master/investigate/github.svg)](https://agentmods.dev/commands/productionmasterai/production-master/investigate)

Your own site

<a href="https://agentmods.dev/commands/productionmasterai/production-master/investigate"><img src="https://agentmods.dev/badge/commands/productionmasterai/production-master/investigate/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/productionmasterai/production-master/investigate"><img src="https://agentmods.dev/badge/commands/productionmasterai/production-master/investigate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 404 The whole file, excluding the scripts and references it only reads on demand.

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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00021	$0.00404
Opus 5.5	$0.00008	$0.00162
Sonnet 5.5	$0.00004	$0.00081
Haiku 4.5	$0.00002	$0.00040

Measured 4d ago against content hash 2a746f691ffc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

investigate 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.

plugin/commands/investigate.md · 33 lines

What it actually says

Start a Production Master investigation for: $ARGUMENTS

The run executes entirely on the Production Master hosted service. You only relay the request and the results through the plugin's production-master MCP server — do no analysis of your own and do not read the user's code for it.

Call mcp__plugin_production-master_production-master__start_investigation with input set to the text above. If the argument is empty, ask the user for a ticket key or a bug description first.
Tell the user the returned investigationId and console link.
Follow progress with mcp__plugin_production-master_production-master__get_investigation, passing investigationId and the cursor from the previous response. After each call, summarise only what is new (phase changes, findings, proposed actions) in a line or two. Stop when the response reports the run is done, or when it asks for a decision.
When the run is done, call mcp__plugin_production-master_production-master__get_report and present the report.
If a step proposes an action, show it to the user and wait for their answer. Never approve or reject on their behalf — they decide on the investigation's page in the Production Master console (the console link from step 2). /production-master:update can list what is waiting.

If a call fails with an authentication error, the access token is missing, expired or revoked: tell the user to run /production-master:setup. Report any other error as it was returned — never present a failed call as an empty result.

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.

4d ago Changed · +16 lines · -3 tokens per session 2a746f691ffc
9d ago Changed · -5 lines 9cf2afb8aa3c
2mo ago First seen · 22 lines · 24 tokens per session scan A 7ffca27fac12

Subscribe to this mod's changes

investigate is a command published in the GitHub repository ProductionMasterAI/production-master (2 stars, last pushed 3d ago), licensed MIT. It adds 21 tokens to every session and 404 once invoked, about $0.0001 per session on Opus 5.5. 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.

Backend and APIs Claude Code DevOps and cloud Research codex cursor incident-investigation mcp

investigate next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
investigateProductionMasterAI/production-master	Command	2	3d ago	MIT	A	21	Claude Code
api-mockwshobson/agents	Command	43k	6d ago	MIT	A	19	Claude Code
initfcakyon/claude-codex-settings	Command	1.2k	today	Apache-2.0	A	0	Claude Code
api-contract-reviewMozurok/fhorja.dev	Command	10	1mo ago	MIT	A	64	Claude Code
pn-audit-dataperniemann/pnCore	Command	0	6d ago	MIT	A	42	Claude Code, Cursor
start-10-1minicoohei/ai-agent-camp	Command	349	1mo ago	none	A	2	Claude Code
design-api-integrationAmey-Thakur/AI-SKILLS	Command	14	2mo ago	MIT	A	16	Claude Code