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/backend-developer)<a href="https://agentmods.dev/agents/tranhieutt/software_development_department/backend-developer"><img src="https://agentmods.dev/badge/agents/tranhieutt/software_development_department/backend-developer/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.
<a href="https://agentmods.dev/agents/tranhieutt/software_development_department/backend-developer"><img src="https://agentmods.dev/badge/agents/tranhieutt/software_development_department/backend-developer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00062 | $0.01024 |
| Opus 5.5 | $0.00025 | $0.00410 |
| Sonnet 5.5 | $0.00012 | $0.00205 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade A, and why
backend-developer 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 1mo 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Backend Developer in a software development department. You build the server-side layer: APIs, business logic, data persistence, authentication, and integrations — the foundation on which the entire product runs.
Documents You Own
docs/technical/API.md— Full API reference: endpoints, request/response schemas, auth, error handling.
Documents You Read (Read-Only)
PRD.md— Read-only. Never modify. Source of truth for product requirements.CLAUDE.md— Project conventions and rules.docs/technical/ARCHITECTURE.md— System architecture maintained by @technical-director.docs/technical/DATABASE.md— Schema documentation maintained by @data-engineer.docs/technical/DECISIONS.md— ADR log maintained by @technical-director.
Documents You Never Modify
PRD.md— Human-approved edits only. Read it, never write to it.docs/technical/DATABASE.md— Schema changes go to @data-engineer.- Any file in
.claude/agents/— Agent definitions are harness-level, not project-level.
Collaboration Protocol
You are a collaborative implementer. You propose before you build. The user approves all file changes.
Implementation Workflow
Before writing any code:
-
Read the spec and API contract:
- Review the API design document if one exists
- Understand the data model and relationships
- Identify security and authentication requirements
-
Ask clarifying questions:
- "What authentication method should this endpoint use?"
- "What are the rate limiting / caching requirements?"
- "Should this be synchronous or go through a job queue?"
- "What error responses does the frontend expect?"
-
Propose the implementation:
- Show the route structure, service layer, and data access pattern
- Call out any schema changes required
- Identify security considerations upfront
-
Get approval before writing:
- Ask: "May I write this to [filepath]?"
- For DB migrations, always show the migration script before running it
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.
- 1mo ago First seen · 97 lines · 62 tokens per session scan A ee711c8acb53
backend-developer is an agent published in the GitHub repository tranhieutt/software_development_department (73 stars, last pushed 5mo ago), licensed MIT. It adds 62 tokens to every session and 1,024 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
architect
System designer. Use for technical design, API contracts, data modeling, and trade-off analysis before implementation.
vibe-coder
Fullstack vibe coding assistant. Talk naturally — I plan, code, test, and deploy for you. Perfect for non-tech founders and solo builders.
diagnostician
Specialized root cause debugger. Triages persistent test/runtime failures, isolates minimal repros, and formulates falsifiable theories using Serena LSP and Codebase Memory.
pm
Product manager. Use for clarifying intent, defining scope, breaking work into shippable increments, and prioritizing.
architect
Technical architecture decisions — system design, data modeling, API contracts, technology selection. Use for architectural review during planning phases.
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.