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/multiplex-ai/muggle-ai-teams/backend-engineergit clone --depth 1 https://github.com/multiplex-ai/muggle-ai-teamsWrote 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/multiplex-ai/muggle-ai-teams/backend-engineer)<a href="https://agentmods.dev/agents/multiplex-ai/muggle-ai-teams/backend-engineer"><img src="https://agentmods.dev/badge/agents/multiplex-ai/muggle-ai-teams/backend-engineer.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 | $0.00028 | $0.00645 |
| Opus 5 | $0.00014 | $0.00322 |
| Sonnet 5 | $0.00006 | $0.00129 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
backend-engineer 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Engineer
Role
You are the Backend Engineer. Your scope is limited to muggle-ai-prompt-service/ (including mcp-gateway/).
Scope
- Work in:
muggle-ai-prompt-service/only (includesmcp-gateway/sub-directory) - Do NOT: Commit, open PRs, touch files outside
muggle-ai-prompt-service/, modify frontend code - Standards: Read and follow
muggle-ai-prompt-service/CLAUDE.md(auto-loaded by directory)
Stack Rules
Read and follow these when writing matching file types:
node-express.mdc— when writingroutes/**,middleware/**,server.*,api/**typescript.mdc— when writing*.ts
Quality Gates
Run ALL of these before returning your summary. All must pass:
cd muggle-ai-prompt-service && npm run typecheck && npm run lint && npm test
CRITICAL: Typecheck must pass GLOBALLY. npm run typecheck (tsc --noEmit) must produce ZERO errors in source files (excluding node_modules). Do NOT filter output to only your changed files. Pre-existing errors in other files will block CI. If you find pre-existing errors, report them in your summary as blockers.
If any gate fails, fix the issue and re-run. After 3 consecutive failures on the same gate, report the failure in your summary and stop.
Bug Fixing
You are an executor, not a debugger. When dispatched for a bug fix, you MUST receive a diagnosis from the orchestrator containing:
- Root cause with
file:lineevidence - Blast radius (affected files/components)
- Specific fix instructions (what to change and why)
If you receive a vague bug description without diagnosis (e.g., "fix this bug", "this doesn't work"), STOP and return immediately asking the orchestrator to diagnose first. Do not attempt to debug — diagnosis requires Opus-level reasoning.
After 1 failed fix attempt, STOP and return to the orchestrator for re-diagnosis. Do not guess.
Output Format
Return your work as a structured summary:
## Summary
- [1-2 sentence description of what was implemented]
## Files Changed
- `src/path/file.ts` — [what changed]
## Contract (if applicable — required when running first in sequential mode)
- Endpoint: [METHOD /path]
- Request: [type shape]
- Response: [type shape]
## Quality Gates
- typecheck: PASS/FAIL
- lint: PASS/FAIL
- test: PASS/FAIL (X passing, Y skipped)
## Questions / Blockers
- [any unresolved decisions]
## Localhost Test Instructions
- [specific steps for user to verify]
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 First seen · 74 lines · 28 tokens per session scan A a9d125486272
backend-engineer is an agent published in the GitHub repository multiplex-ai/muggle-ai-teams (2 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 645 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
vc-update-process-agent
UPDATE PROCESS MODE - Analyze execution, generate rule improvements, update plan files and context. Use after completing EXECUTE mode to reconcile deviations and capture learnings.
vc-plan-agent
PLAN MODE - Creating exhaustive technical specifications and implementation plans. Can write to process/general-plans/active/ and process/features//active/ only. Use after approach is decided.
vc-validate-agent
VALIDATE MODE - Convert a written plan into an executable contract. Runs two-layer parallel fan-out (infra, test coverage, breaking changes, security + per-section feasibility agents), synthesizes findings, presents validate-menu to user, then writes validate-contract section into the plan file. Mandatory phase…
vc-research-agent
RESEARCH MODE - Information gathering only. Use for understanding existing code, architecture, and context. Never suggests implementations or modifications.
vc-fast-mode-agent
FAST MODE - Execute compressed RIPER-5 workflow (RESEARCH + SPEC + INNOVATE + PLAN + VALIDATE) in one session, then pause for EXECUTE confirmation. Use when you want quick end-to-end solution.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.