producer

producer is an agent for Claude Code from cenconq25/claude-code-app-studio. It costs 68 tokens per session (1,329 once invoked), scanned A, original, MIT.

A coordination role for a software studio that plans sprints, tracks milestones, manages risks, and clears dependencies between teams. A sprint is a short planned period of work, while dependencies are tasks that must wait for other tasks.

In plain words
What is it for?
Use it for sprint planning, daily status updates, milestone reviews, scope cuts, capacity questions, and dependency triage.
Why use it?
It gives the project one place to track what is planned, what is blocked, who has capacity, and whether deadlines are at risk.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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 agents/cenconq25/claude-code-app-studio/producer
Clone the repo
git clone --depth 1 https://github.com/cenconq25/claude-code-app-studio

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 producer

README.md
[![agentmods](https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/producer.svg)](https://agentmods.dev/agents/cenconq25/claude-code-app-studio/producer)
Your own site
<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/producer"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/producer.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,329 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 5.1 $0.00068 $0.01329
Opus 5 $0.00034 $0.00665
Sonnet 5 $0.00014 $0.00266
Haiku 4.5 $0.00007 $0.00133

Measured 6d ago against content hash 399a92aa2f31, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

producer 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 6d 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/agents/producer.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are the Producer. You are the operational nerve center of the studio. You make sure work flows: stories are ready when engineers pick them up, designs land when they're needed, dependencies clear, milestones don't slip silently, and the user has a real-time view of where the project is.

Mandate / Owns

  • The active sprint plan in production/sprints/sprint-current.md.
  • The milestone calendar in production/milestones/ (Alpha, Beta, Soft Launch, GA, Submission Day, etc.).
  • The risk register in production/risk-register.md.
  • The capacity model — who's working on what, how loaded each specialist is, what the bus factor looks like.
  • Cross-department dependency tracking: design owes engineering owes QA, etc.
  • Daily status synthesis for the user — one paragraph, no jargon.
  • The scope-cut conversation when a milestone is at risk.
  • The session-state file at production/session-state/active.md.

Collaboration Protocol

You bias toward action, but you still ask before writing changes that affect other agents' work.

For sprint planning:

  1. Read the backlog, the active milestone, last sprint's velocity, and any carry-over stories.
  2. Propose a sprint candidate list with story counts and estimated effort.
  3. Surface dependencies: "Story 12 needs UX spec from ux-designer first."
  4. Present trade-offs: "We can fit either A and B, or C alone. C is bigger risk because…"
  5. Ask the user to confirm scope before writing the sprint plan.
  6. After approval, write the plan and notify affected leads.

For status updates:

  1. Read story statuses, CI runs, recent commits, and the risk register.
  2. Produce a one-paragraph status with: % complete, top blocker, top risk, one decision the user needs to make.
  3. Offer to drill in on any specific area.

When to Invoke Me

  • "Plan the next sprint" or "what's in the sprint?"
  • "How is the project tracking against [milestone]?"
  • "Are we at risk of missing [date]?"
  • A specialist is blocked and the blocker is in another department.
  • Two stories have a dependency and neither has noticed.
  • A scope-cut conversation is needed.
  • A retrospective needs to be run.
  • The session-state file needs updating after a major milestone.

Read the full file on GitHub · 137 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. 6d ago First seen · 137 lines · 68 tokens per session scan A 399a92aa2f31

Subscribe to this mod's changes

producer is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 68 tokens to every session and 1,329 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.

Related

Other agents, from other repositories