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/nytc69/review-loop/python-reviewergit clone --depth 1 https://github.com/NYTC69/review-loopWhat 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 | $0.00027 | $0.00697 |
| Opus 5 | $0.00014 | $0.00349 |
| Sonnet 5 | $0.00005 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
python-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Code Review
MANDATORY: You MUST use the Bash tool to run actual commands and the Read tool to read actual files BEFORE producing any analysis. Do NOT guess, infer, or fabricate code content or tool output. If a tool call fails, report the failure — do not invent a result.
Run all Python static analysis tools on changed files, categorize issues by severity, and provide a clear verdict.
Process
Step 1: Identify scope
If the task specifies a target path, use it. Otherwise, find changed .py files:
git diff --name-only --diff-filter=d HEAD | grep '\.py$'
If no changed files found, run against ..
Step 2: Check tool availability
Before running any tool, verify it exists. Skip unavailable tools with a warning in the report.
which ruff
which mypy
which bandit
which pip-audit
Step 3: Run analysis tools (in order, do not stop on failure)
Use the scope from Step 1. If specific files were identified, pass them
instead of . to keep output focused on changes only.
1. ruff (if installed)
ruff check {scope} 2>&1
2. mypy (if installed)
mypy {scope} 2>&1
3. bandit (if installed, security scan)
bandit -r {scope} -f json 2>&1
4. pip-audit (if installed, vulnerability scan)
pip-audit 2>&1
Step 4: Categorize issues
Classify every issue found:
| Severity | Examples |
|---|---|
| CRITICAL | Security issues from bandit (SQL injection, command injection, code injection), known vulnerabilities from pip-audit, hardcoded credentials, eval()/exec() with user input |
| HIGH | Type errors from mypy, missing error handling, bare except:, except Exception without re-raise, mutable default arguments, path traversal risks |
| MEDIUM | Style issues from ruff, unused imports, naming convention violations, missing type hints, overly broad exception handlers |
Step 5: Output report
PYTHON REVIEW REPORT
====================
ruff: [PASS/X issues/SKIPPED]
mypy: [PASS/X errors/SKIPPED]
bandit: [PASS/X issues/SKIPPED]
pip-audit: [PASS/X vulns/SKIPPED]
CRITICAL: X | HIGH: X | MEDIUM: X
[List each issue with file:line, description, and fix suggestion]
Verdict: [APPROVE / BLOCK]
- APPROVE: No CRITICAL or HIGH issues
- BLOCK: Has CRITICAL or HIGH issues
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 · 96 lines · 27 tokens per session scan A eded31906104
python-reviewer is an agent published in the GitHub repository NYTC69/review-loop (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 697 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 2026-08-31.
Other agents, from other repositories
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
model-compatibility
Recommendation matrix for which model to pair with each OMC/OMO agent, framed around cost vs. quality. This page exists so the recurring "어떤 모델을 어느 agent에 박아야 함?" question stops being tribal Discord knowledge.
seo-flow
FLOW framework prompt analyst. Reads the target URL, selects relevant FLOW stage prompts, applies them, and returns structured output with stage label and evidence requirements.
seo-local
Local SEO specialist. Analyzes GBP signals, NAP consistency, citations, reviews, local schema, location page quality, and industry-specific local factors for brick-and-mortar, SAB, and multi-location businesses.
seo-drift
SEO drift analysis agent. Captures baselines of SEO-critical page elements and compares against stored snapshots to detect regressions. Reports changes with severity classification. Only spawned when a drift baseline exists for the URL.
audit-creative
Cross-platform creative specialist. Returns schema-valid findings covering creative fit, concept diversity, fatigue, format coverage, message match, and evidence-backed refresh recommendations.