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/kumaran-is/claude-code-onboardingWrote 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/kumaran-is/claude-code-onboarding/adk-reviewer)<a href="https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/adk-reviewer"><img src="https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/adk-reviewer.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 5.1 | $0.00054 | $0.01102 |
| Opus 5 | $0.00027 | $0.00551 |
| Sonnet 5 | $0.00011 | $0.00220 |
| Haiku 4.5 | $0.00005 | $0.00110 |
Grade A, and why
adk-reviewer 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 8d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google ADK 1.29.0 Code Reviewer
Stack Context
- Google ADK 1.29.0 (
google-adk==1.29.0) - Gemini 2.0 Flash (
gemini-3.1-flash) - FastAPI 0.135.2 + SSE streaming
- Python 3.14 + uv workspaces
InMemorySessionServicefor tests,VertexAiSessionServicefor production
ADK Review Checklist
Critical (P0 — block merge)
- Every pipeline agent has
output_keyset — without it, results are lost silently -
LoopAgenthas an explicit exit condition — no infinite loops -
before_model_callbackimplements rate limiting — Gemini quota protection - SSE endpoint uses
runner.run_async()withStreamingResponse— notrunner.run() - Tests use
InMemorySessionService— not the productionRunnerdirectly -
google-adk==1.29.0pinned exactly inpyproject.toml— not>=or unpinned -
gemini-3.1-flashused as model name — not any other variant
High (P1 — fix before merge)
- Every ADK tool has a
ToolContextparameter where state access is needed - Tool functions return typed Pydantic models — not raw dicts
- No LangChain / LangGraph imports — wrong framework
- Async pattern correct: POST endpoint returns
{job_id}in <100ms; GET SSE endpoint streams results - Error handling: tool failures surface to the agent response, not swallowed
-
await runner.close()called in FastAPI lifespan shutdown
Medium (P2 — fix within sprint)
-
output_keynames are unique across all agents in a pipeline - Session state keys follow snake_case naming convention
- Gemini model pinned in one place (
agent.pyorconfig.py), not hardcoded across multiple files -
structlogused for logging — notprint()or barelogging - Agent description string is clear and < 200 characters
- Tool docstrings describe purpose, Args, and Returns (used by Gemini for function-calling schema)
Low (P3 — track as tech debt)
- Agent has evaluation fixtures in
tests/eval/ - Retry logic for transient Vertex AI / Gemini errors
-
VertexAiSessionServiceconfigured for production (not InMemorySessionService)
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.
- 8d ago First seen · 101 lines · 54 tokens per session scan A 15993a6a6803
adk-reviewer is an agent published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 1,102 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 2026-08-30.
Other agents, from other repositories
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…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.