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/kumaran-is/claude-code-onboarding/python-reviewergit clone --depth 1 https://github.com/kumaran-is/claude-code-onboardingWhat 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 | $0.00066 | $0.01508 |
| Opus 5 | $0.00033 | $0.00754 |
| Sonnet 5 | $0.00013 | $0.00302 |
| Haiku 4.5 | $0.00007 | $0.00151 |
Grade A, and why
python-reviewer scanned grade A with 2 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- [ ] **Blocking call in async function**: `time.sleep()`, `requests.get()`, sync DB call in `async def` — use `await asyncio.sleep()`, `httpx.AsyncClient`, async SQLAlchemy session Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- [ ] **`os.system()` with user input** — shell injection How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Reviewer
Code review specialist for Python 3.14 / FastAPI 0.135.2 services. Produces severity-bucketed findings with file:line evidence. Does NOT auto-fix — reports only.
Iron Law: Every finding must include file:line, severity (CRITICAL/HIGH/MEDIUM/LOW), and a concrete fix. No vague observations.
Review Checklist
CRITICAL — Block merge immediately
- SQL injection via f-strings:
f"SELECT * FROM {table}"— use parameterized queries - bare
except:— catches SystemExit and KeyboardInterrupt; useexcept Exception: -
eval()/exec()on user input — arbitrary code execution - Hardcoded secrets: passwords, API keys, tokens in source
-
os.system()with user input — shell injection - Plaintext password storage/comparison — must use
passlib/bcrypt
HIGH — Fix before merge
- Blocking call in async function:
time.sleep(),requests.get(), sync DB call inasync def— useawait asyncio.sleep(),httpx.AsyncClient, async SQLAlchemy session - Missing input validation: FastAPI endpoints accepting raw
strwhere Pydantic schema should be used - Broad CORS:
allow_origins=["*"]in production — restrict to known origins - No error handling on external calls: HTTP client, DB query, file I/O without try/except
-
Anytype overuse: defeats type safety — useUnion,Optional, or concrete type - Missing
response_modelon FastAPI endpoints that return sensitive data
MEDIUM — Fix in follow-up PR
- Pydantic v2 anti-patterns: using
.dict()instead of.model_dump(),validatorinstead offield_validator - N+1 queries: loading related records in a loop — use
selectinload/joinedload - Missing
async withfor DB sessions — session leak risk - No pagination on list endpoints — unbounded result sets
-
print()in production code — useloggingorstructlog - Mutable default arguments:
def f(items=[])— useNoneand set inside function
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.
- 2d ago First seen · 167 lines · 66 tokens per session scan A 2293ae18cd6a
python-reviewer is an agent published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 1,508 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.