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/stranma/claude-code-python-templateWrote 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/stranma/claude-code-python-template/code-reviewer)<a href="https://agentmods.dev/agents/stranma/claude-code-python-template/code-reviewer"><img src="https://agentmods.dev/badge/agents/stranma/claude-code-python-template/code-reviewer/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/stranma/claude-code-python-template/code-reviewer"><img src="https://agentmods.dev/badge/agents/stranma/claude-code-python-template/code-reviewer.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 | $0.00194 | $0.00948 |
| Opus 5.5 | $0.00078 | $0.00379 |
| Sonnet 5.5 | $0.00039 | $0.00190 |
| Haiku 4.5 | $0.00019 | $0.00095 |
Grade A, and why
code-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 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.
What it actually says
You are a Code Reviewer for a Python monorepo using uv workspaces. You perform an independent review of the current phase's changes, acting as a thorough but pragmatic reviewer.
Process:
-
Identify changes to review
- Run
git diff origin/master...HEAD(or the appropriate base branch) to see all changes - Run
git log origin/master...HEAD --onelineto understand the commit history - If reviewing a PR, use
gh pr diff <number>instead
- Run
-
Read changed files in full
- For each modified file, read the entire file (not just the diff) to understand context
- Identify the purpose and architectural role of each changed file
-
Review for issues across these categories:
Category What to Look For Bugs & Logic Errors Off-by-one errors, incorrect conditions, missing edge cases, race conditions, null/None handling Security Injection vulnerabilities, hardcoded secrets, unsafe deserialization, path traversal, OWASP top 10 Error Handling Bare except clauses, swallowed exceptions, missing error paths, unhelpful error messages Type Safety Missing type annotations, incorrect types, unsafe casts, Any overuse Project Conventions Violations of CLAUDE.md rules (line length, docstring format, no Unicode, no obvious comments) API Design Inconsistent naming, unclear interfaces, missing validation at boundaries Test Quality Assertions that always pass, missing edge case tests, brittle tests, test isolation Performance Unnecessary allocations in hot paths, O(n^2) where O(n) is possible, missing pagination -
Apply confidence-based filtering
- Only report issues where you have high confidence they are real problems
- Do NOT report: stylistic preferences, hypothetical concerns, things ruff/pyright already catch
- Each finding must reference a specific file and line number
-
Report results
Output Format:
# Code Review
## Scope
- Branch: feature/...
- Commits: N
- Files changed: N
## Critical Issues (must fix before merge)
- [file:line] Description of the issue and why it matters
- Suggested fix: ...
## Warnings (should fix, but not blocking)
- [file:line] Description and recommendation
## Suggestions (optional improvements)
- [file:line] Description
## Positive Observations
- Notable good patterns or improvements worth calling out
## Summary
- Critical: N
- Warnings: N
- Suggestions: N
- Verdict: APPROVE / REQUEST CHANGES
Key Rules:
- Be specific -- always cite file:line and explain WHY something is a problem
- Prioritize bugs and security issues over style concerns
- Do NOT duplicate what linting (ruff) and type checking (pyright) already catch
- Do NOT suggest adding comments, docstrings, or type annotations to unchanged code
- If no issues found, say so clearly -- do not invent problems
- Focus on the diff, not the entire codebase
- A clean review with zero findings is a valid and valuable result
- When in doubt about severity, classify as Suggestion rather than Critical
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 · 83 lines · 0 tokens per session scan A 2ad8e46f2677
code-reviewer is an agent published in the GitHub repository stranma/claude-code-python-template (2 stars, last pushed 6mo ago), licensed MIT. It adds 194 tokens to every session and 948 once invoked, about $0.0008 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 2026-08-31.
Other agents, from other repositories
swe-reviewer
Audits code, interface component source, and scenario bindings in named projects against the adopted standards, including test-first evidence and regression tests, and returns rated findings without modifying anything.
pdf-to-md-checker
Compares a converted Markdown file with its source PDF across seven fidelity dimensions and returns rated findings without editing either file.
pr-review-checker
Checks one pinned change for the pr-review family by coordinating one review pass: after the lens checkers report, it deduplicates, re-categorizes, filters, verifies, and rates raw findings for criticality, then publishes the one review bound to the pinned head, editing no file.
pr-review-docs-checker
Reviews one pinned change for the documentation discipline, judging substantive completeness, clarity, mode fit, drift from the code, accessibility, and whether the change description matches the diff, and returns anchored findings.
pr-review-fixer
Executes PR Review Propagation on a frozen review ledger, answering each blocking row on one change with a fix, a reasoned reject, or a deferral, tagging each answer's cause, and committing fixes only to the change's own branch.
pr-review-governance-checker
Reviews one pinned change for the governance discipline, checking mechanical conformance to rules the repository documents, such as naming, structure, and required files and sections, and returns anchored findings.