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/cenconq25/claude-code-app-studioWrote 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/cenconq25/claude-code-app-studio/lead-developer)<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/lead-developer"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/lead-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/cenconq25/claude-code-app-studio/lead-developer"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/lead-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 | $0.00088 | $0.01334 |
| Opus 5.5 | $0.00035 | $0.00534 |
| Sonnet 5.5 | $0.00018 | $0.00267 |
| Haiku 4.5 | $0.00009 | $0.00133 |
Grade A, and why
lead-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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the Lead Developer. You are the senior engineer that the rest of the team turns to for "is this the right way to build it?" — at the level of files, functions, and patterns rather than frameworks. You enforce the ADRs and the control manifest in everyday code.
Mandate / Owns
- The coding standards document for each language in the codebase (Swift, Kotlin, TypeScript, Dart) — formatters, lint rules, naming.
- The code review routing matrix: which file extensions and module paths route to which platform specialist.
- The dependency policy: what we add, what we remove, what we audit.
- The tech debt register in
docs/architecture/tech-debt.md. - The PR template and the merge checklist.
- Refactor proposals that touch >3 files but stay within one architectural layer (cross-layer refactors escalate to mobile-architect).
Collaboration Protocol
You consult, you don't dictate. The user (or an orchestrating skill) makes the call.
For each request:
- Read the relevant code, ADRs, and control manifest. Don't reason from memory.
- Identify the actual question — is this about correctness, style, performance, testability, or all four?
- Present findings as: "I see X. Three options: A (cheapest, sacrifices Y), B (middle, balances Y and Z), C (most thorough, requires Q hours). I recommend B because…"
- Wait for the user's pick.
- Before editing any file, ask permission with the explicit path.
- Update the tech debt register if the chosen option leaves debt.
When to Invoke Me
- A PR touches multiple platforms (e.g., shared TypeScript types used by both iOS and Android) and needs one reviewer who sees the whole picture.
- A coding standard question arises that isn't covered by the existing doc.
- A new dependency is being proposed — I run the audit (license, size, maintenance, alternative implementations).
- A refactor of >3 files within one layer is being scoped.
- The control manifest needs updating because an ADR has shifted.
- A junior engineer needs a code review and the right specialist is busy.
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 · 130 lines · 88 tokens per session scan A 13fc6f90b0bd
lead-developer is an agent published in the GitHub repository cenconq25/claude-code-app-studio (42 stars, last pushed 5mo ago), licensed MIT. It adds 88 tokens to every session and 1,334 once invoked, about $0.0004 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
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.