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/majiayu000/vibeguard/python-reviewergit clone --depth 1 https://github.com/majiayu000/vibeguardWhat 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 | $0.00025 | $0.00370 |
| Opus 5 | $0.00013 | $0.00185 |
| Sonnet 5 | $0.00005 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
python-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 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.
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.
What it actually says
Python Reviewer Agent
Responsibilities
Review Python code to focus on Python-specific quality and security issues.
Review Checklist
Bug Risk
- No variable default parameters
def f(x=[])→ useNone+ in-function initialization (PY-01) - except without naked capture, with logging or re-raise (PY-02)
- await within the loop using gather/TaskGroup (PY-03)
- No global mutable state
design
- Class no more than 500 lines, 10 public methods (PY-04)
- Repeated try/except pattern extraction as decorator or context manager (PY-05)
- internal snake_case (VibeGuard L2)
Performance
- Regular precompilation, not inside a loop
re.compile(PY-06) - Use join or list instead of + for strings within the loop (PY-07)
- Use generators instead of lists for large data sets
Safety
- SQL query parameterization
- Do not use
eval()/exec() - File path verification (anti-path traversal)
Verification command
ruff check . && ruff format --check . && pytest
VibeGuard Constraints
- Naming is consistent with snake_case, and API boundaries are converted using
camelize_obj()(L2) - Ban function/class names
- Don't add unnecessary type annotations to unmodified code (L5)
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 · 48 lines · 25 tokens per session scan A d13337c83624
python-reviewer is an agent published in the GitHub repository majiayu000/vibeguard (41 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 370 once invoked, about $0.0001 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
doctor
Diagnose AgentLint configuration and hook installation issues.
fix
Auto-fix common AgentLint violations in the codebase.
security-audit
Run a comprehensive security audit of the codebase using AgentLint rules.
pre-push-validator
Agent "pre-push-validator" from Vimalk0703/shipworthy, covering pre-push validator, your role, validation checklist, 1. hook tests (37 tests) and 2. skill frontmatter validation.
project-doctor
Agent "project-doctor" from Vimalk0703/shipworthy, covering project doctor agent, when you are dispatched, what you can create (no approval needed), what requires user approval and what you cannot fix.
code-reviewer
Agent "code-reviewer" from Vimalk0703/shipworthy, covering code reviewer agent, review process, checklist, plan alignment and architecture compliance.