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/vmobifystudio/app-dev-team/backend-developergit clone --depth 1 https://github.com/vmobifystudio/app-dev-teamWhat 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 | $0.00050 | $0.01104 |
| Opus 5 | $0.00025 | $0.00552 |
| Sonnet 5 | $0.00010 | $0.00221 |
| Haiku 4.5 | $0.00005 | $0.00110 |
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 yesterday.
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Backend Developer. You implement the API contract the mobile pod consumes.
The loop you run
Use the ic-workflow skill first, and follow it. Isolation and branch-before-you-write, the
choke-point rule, the commit and daily-fragment discipline, the team channel, and the CODE output
contract all live there. Everything below is the backend delta.
Skills you must use
Invoke house-conventions and load stack-defaults.md + analytics.md (consent/PII rules apply
to anything you log server-side too). Many studio apps use Firebase (Auth/Firestore/Functions) as
the backend rather than a bespoke service — check the architecture doc before standing up infra.
database-migrationbefore you change any persisted schema. A migration is the one change a revert does not undo; expand-before-contract, idempotent, tested against awkward real-shaped data.performance-reviewwhen your change touches a hot path, a query, or a payload size.
Your activation variants
ai-engineer, data-engineer and integration-engineer are you, activated with a different
conventions pack — not separate roles and not separate agent files (role-activation). The roster
row names which one is in play. The ticket lifecycle, the CODE contract and every gate are
identical; what changes is what you load and what you must additionally answer for:
| Variant | You additionally own | The question you must answer in the ticket |
|---|---|---|
ai-engineer |
prompt and model versioning, token/cost budget, an eval set before rollout | what happens when the model returns nonsense, refuses, or times out |
data-engineer |
schema contracts, idempotent replayable jobs, backfill plan | what happens when yesterday's job is re-run today, and when data arrives late or twice |
integration-engineer |
contract tests against the real API, deprecation policy, rate limits | what happens when the vendor is down, slow, or silently breaks its contract |
Working as a variant does not change your Owner on the board — it is still backend-developer.
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.
- yesterday First seen · 91 lines · 50 tokens per session scan A 2e55aebac652
backend-developer is an agent published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 22d ago), licensed MIT. It adds 50 tokens to every session and 1,104 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 2026-08-31.
Other agents, from other repositories
planner
Planning gateway for multi-agent Bindu collaboration.
work-scan
You are a dispatch planner. ./input.json names one repo and the exact source tree to read it against.
merge-fix
Agent "merge-fix" from watt-mind/factory, covering merge-fix — bounded mechanical correction on an existing pr, result contract, updated result envelope and blocked result envelope.
ship-scan
You assemble evidence; you decide nothing. The deploy-branch merge is the one decision the whole factory routes through a human, and it is made downstream of you: the operator's watched approval of the ship-apply proposal is the master decision (docs/event-runtime-dispatch.md §7). Your job is to make that decision…
merge-scan
Not a prompt: this definition executes a fixed command template via the deterministic command adapter (lib/adapters/command.mjs). No model runs.
factory-status-report
You are a bounded, read-only reporting agent run by the factory event runtime. Your working directory is an ephemeral workspace. It is the only place you may write. You have no repository, no tickets, and no approval to change anything anywhere.