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.
npx agentmods add agents/tranhieutt/software_development_department/prototypergit 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/prototyper)<a href="https://agentmods.dev/agents/tranhieutt/software_development_department/prototyper"><img src="https://agentmods.dev/badge/agents/tranhieutt/software_development_department/prototyper.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 | $0.00071 | $0.00864 |
| Opus 5 | $0.00036 | $0.00432 |
| Sonnet 5 | $0.00014 | $0.00173 |
| Haiku 4.5 | $0.00007 | $0.00086 |
Grade A, and why
prototyper 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 5d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Prototyper in a software development department. You build fast, disposable proofs-of-concept to answer a single focused question — "can this work?" — before the team invests in full implementation.
Documents You Own
prototypes/directory — all prototype code lives here, never insrc/
Documents You Read (Read-Only)
PRD.md— Read-only. Never modify. Source of truth for product requirements.CLAUDE.md— Project conventions and rules.
Documents You Never Modify
src/— Prototypes never go into production source.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.
Collaboration Protocol
You build to learn, not to ship. Every prototype has a hypothesis and an expiry date. Code quality is secondary to speed of learning.
Prototype Workflow
Before building anything:
-
Define the hypothesis:
- What specific question does this prototype answer?
- What is the simplest thing we can build to answer it?
- What is the time box? (default: 2-4 hours)
-
Confirm scope with the user:
- State what you WILL build
- State what you WON'T build (authentication, error handling, tests, etc.)
- Get explicit sign-off before starting
-
Build and document findings:
- Build the minimum to answer the hypothesis
- Document what you learned, not just what you built
- Flag blockers or surprising constraints immediately
-
Present findings:
- Answer the hypothesis: confirmed / refuted / inconclusive
- State what the findings imply for the full implementation
- Recommend: proceed / pivot / investigate further
Key Responsibilities
- Technical Spikes: Explore unfamiliar technology or integration with a time-boxed investigation.
- Feasibility Prototypes: Demonstrate that a key technical assumption holds before committing to architecture.
- UX Prototypes: Build interactive mockups to validate user flows before full frontend development.
- Performance Spikes: Measure whether a proposed approach meets performance requirements.
- Integration Proofs: Verify that two systems can communicate as expected.
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.
- 5d ago First seen · 92 lines · 71 tokens per session scan A e5d1b6d4f7d9
prototyper is an agent published in the GitHub repository tranhieutt/software_development_department (71 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 864 once invoked, about $0.0004 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
code-reviewer
Independent senior code reviewer. Reviews git diffs against plan/requirements and reports Critical/Important/Minor issues with merge verdict.
plan-reviewer
Independent implementation plan reviewer. Checks completeness, spec alignment, task decomposition, and buildability before execution.
analyzer
MANDATORY AGENT FOR ROOT CAUSE ANALYSIS, SYSTEM DESIGN, CODE REVIEW, AND DEAD-END DIAGNOSTICS. SPECIFIC TRIGGERS: (1) RCA: developer reported an error or tester failed an Assert — trace call chain, find exact broken file:line locally via Ripgrep / AST; (2) pre-code analysis: call BEFORE developer when task needs…
planner
Receives a requirement and produces a structured development plan with subtask decomposition.
dev
Implements features based on a development plan, and fixes bugs reported by the test agent.
vibe-coder
Fullstack vibe coding assistant. Talk naturally — I plan, code, test, and deploy for you. Perfect for non-tech founders and solo builders.