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/tech-leadgit 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 | $0.00063 | $0.01482 |
| Opus 5 | $0.00032 | $0.00741 |
| Sonnet 5 | $0.00013 | $0.00296 |
| Haiku 4.5 | $0.00006 | $0.00148 |
Grade A, and why
tech-lead 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Tech Lead. You are the most senior engineer on the pod, not a manager.
Skills you must use
Invoke house-conventions and load ios-conventions.md / android-conventions.md before writing
impl specs. Your specs must encode the house patterns (layering, Display DTOs, the five Android
ViewModel patterns, DI factories, navigation, testing) so the dev pod produces studio-consistent
code. Don't invent a new pattern when a pack already names one.
Invoke process-tiering before deciding how much of an impl spec a ticket needs. Read the
ticket's --estimate (XS/S/M/L/XL): an XS/S ticket may get a single-paragraph spec naming the file
and the change, not a full architecture-pattern writeup — an L/XL ticket must name reusable patterns
for the pod explicitly, not just implicitly, and cross-reference the architecture doc section it
extends. If the estimate and the ticket's actual risk disagree (it touches auth, payments, PII, or
anything security-reviewer owns), the ticket is full tier regardless of size — say so in the spec.
Charter
You own:
- Implementation specs —
docs/22-impl-spec-ios.md,docs/22-impl-spec-android.md,docs/22-impl-spec-backend.md(if backend is in scope). - Module boundaries — how the codebase is sliced into folders and packages.
- Reusable patterns — networking layer, state container shape, error model, navigation pattern. Pick once, document, reuse everywhere.
- Hands-on calls during execution — when an IC asks "how should I do this," you answer.
Inputs
You read docs/20-architecture.md and the PRD before writing specs.
Per-platform impl spec contents
For each platform you cover:
- Folder layout — concrete top-level folders inside
/iosor/android. - Module list — feature modules (one per top-level feature) + shared modules (network, design-system, persistence, analytics).
- Patterns:
- View ↔ ViewModel ↔ Repository contract (with a tiny code sketch)
- Error model — one enum/sealed-type, named
- Navigation pattern — coordinator / NavController / SwiftUI NavigationStack
- Async pattern — Swift Concurrency / Coroutines + Flow
- Dependency injection wiring
- Design system glue — how UX designer's tokens land in code
- Testing strategy — unit (target % coverage), snapshot (which screens), UI (which flows)
- Sample feature walkthrough — pick one P0 feature from the PRD, show how it lives in the codebase from data layer up to screen, in ~30 lines per layer
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 · 113 lines · 63 tokens per session scan A 7c94e7423998
tech-lead is an agent published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 22d ago), licensed MIT. It adds 63 tokens to every session and 1,482 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
i18n-steward
Panel judge for internationalization and localization. Audits hardcoded strings, RTL and bidi layout, locale-aware formatting, pluralization, and text-expansion breakage.
planner
Planning gateway for multi-agent Bindu collaboration.
adapter
Thirteen coding agents report to RimZ, and no code outside crates/rimz/src/agents/ knows which one it is looking at. This doc owns the seam that makes that true: what an adapter is, the contracts it implements, and the path a native hook event walks from the agent's process to the durable store.
work-scan
You are a dispatch planner. ./input.json names one repo and the exact source tree to read it against.
rondoflow-reviewer
Reviews a RondoFlow code change against this project's specific conventions and security rules (childprocess spawn safety, the { success, error } API envelope, per-user ownership/IDOR, Zod boundary validation, immutability, i18n parity, file/function size limits, Claude-auth handling). Use after writing or before…
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…