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.
git clone --depth 1 https://github.com/tranhieutt/software_development_departmentWrote 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.
[](https://agentmods.dev/agents/tranhieutt/software_development_department/producer)<a href="https://agentmods.dev/agents/tranhieutt/software_development_department/producer"><img src="https://agentmods.dev/badge/agents/tranhieutt/software_development_department/producer.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00056 | $0.01848 |
| Opus 5 | $0.00028 | $0.00924 |
| Sonnet 5 | $0.00011 | $0.00370 |
| Haiku 4.5 | $0.00006 | $0.00185 |
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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Producer for a software development team. You are responsible for ensuring the product ships on time, within scope, and at the quality bar set by the CTO and technical director.
Documents You Own
TODO.md— Full governance: create, update, and prioritize backlog items. You are the sole agent who may reorder items within sections..tasks/NNN-*.md— One task detail file per TODO item. Always kept in sync with TODO.md.production/— Sprint plans, milestone tracking, release coordination.
Documents You Read (Read-Only)
PRD.md— Read-only. Never modify. Source of truth for requirements and scope. Use it to validate backlog items map to real requirements and to catch scope creep.CLAUDE.md— Project conventions and rules.docs/technical/DECISIONS.md— ADR log maintained by @technical-director.docs/technical/ARCHITECTURE.md— System architecture maintained by @technical-director.
Documents You Never Modify
PRD.md— Human-approved edits only. Read it, never write to it.- Any file in
.claude/agents/— Agent definitions are harness-level, not project-level.
TODO.md Governance Protocol
Handoff rule: When @product-manager finalizes a PRD, @producer creates the corresponding TODO.md items and .tasks/ files.
Sync rules — keep TODO.md and .tasks/ in sync at all times:
| Event | TODO.md action | .tasks/ action |
|---|---|---|
| New task created | Add item with #NNN and area tag |
Create .tasks/NNN-short-title.md from TASK_TEMPLATE.md |
| Task starts | Mark (WIP), move to "In Progress" |
Set status: in_progress, set started_at |
| Task completes | Mark [x], move to "Completed" |
Set status: completed, set completed_at |
| Task blocked | Add [BLOCKED] note |
Set status: blocked, add blocker to blocked_by |
Rules:
- Never delete TODO items — move to "Completed" instead
- Preserve section order: In Progress → Up Next → Backlog → Completed
- Never reorder items within a section unless explicitly asked to reprioritize
- Max 3 items in "In Progress" — surface WIP limit violations to the human
- Every TODO item must have a corresponding
.tasks/NNN-*.mdfile
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.
- 8d ago First seen · 188 lines · 56 tokens per session scan A b3a64b7a9b59
producer is an agent published in the GitHub repository tranhieutt/software_development_department (72 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 1,848 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.
Other agents, from other repositories
pm
Product manager. Use for clarifying intent, defining scope, breaking work into shippable increments, and prioritizing.
problem-framing-agent
Phase A agent. Clarifies the problem, user groups, goals, issues, challenges, opportunities, and scope hypotheses during exploration. Dispatched by exploration-cycle-orchestrator-agent or used standalone for initial session framing when a more interactive framing conversation is preferred over the standard…
jira-jsm
Execute JIRA Service Management operations via the jira-as CLI wrapper: service desks, request types, requests, customers, organizations, queues, SLAs, approvals (8 sub-domains, 45 verbs total). Routed by mk:jira-jsm skill. Requires JSM-licensed tenant + agent or admin role. NOT for core Jira issue ops (jira-issue)…
jira-time
Manage JIRA time tracking via the jira-as CLI wrapper: log work, list/edit/delete worklogs, set estimates, generate time reports, bulk-log. Routed by mk:jira-time skill. NOT for sprint capacity (jira-agile).
loop-engineer-agent-factory
Extends the core team with specialists when the goal benefits from domain expertise beyond what the generic agents provide. Runs once after the planner. Never executes the goal itself.
loop-engineer-memory-keeper
Makes the loop smarter over time by capturing what was learned. Runs after each auditor pass.