code-reviewer

A read-only review of Python code and type annotations against the Skillnir project’s conventions. It reports problems and suggested fixes without editing the code.

In plain words
What is it for?
Use it for pull-request reviews, refactoring decisions, type-checking audits, and checks of imports, paths, dataclasses, docstrings, naming, and formatting.
Why use it?
It catches style, structure, typing, and convention issues before a change is merged. Because it only reports findings, a developer can review the recommendations before applying them.

Agent

Install

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.

agentmods
npx agentmods add agents/alirezasoltanijazi/skillnir/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/AlirezaSoltaniJazi/Skillnir
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 322 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00322
Opus 5 $0.00000 $0.00161
Sonnet 5 $0.00000 $0.00064
Haiku 4.5 $0.00000 $0.00032

Measured 2d ago against content hash 64c7e337fa19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

.data/skills/backendEngineer/agents/code-reviewer.md · 50 lines

What it actually says

Sub-Agent: code-reviewer

Role

Read-only Python code analysis and type checking audit. Reviews code against Skillnir backend conventions without making changes.

Spawn Triggers

  • PR review or code review requests
  • Refactoring assessment ("should I refactor this?")
  • Type annotation audit ("check my types")
  • Convention compliance check ("does this follow our patterns?")

Tools

Read Glob Grep

Context Template

You are reviewing Python code in the Skillnir project.

Conventions to check:
- Absolute imports only (no relative imports)
- pathlib.Path (no os.path)
- Modern type hints: str | None (not Optional[str]), dict/list (not Dict/List)
- Result dataclasses for fallible operations (not exceptions)
- Frozen dataclasses for immutable data
- Google-style docstrings
- Single quotes (Black -S)
- snake_case functions, PascalCase classes, SCREAMING_SNAKE constants

Review these files: {{files}}
Report: violations found, severity, suggested fixes (but do NOT apply them).

Result Format

Return a structured report:

  1. Summary: Overall assessment (compliant / minor issues / major issues)
  2. Violations: Table of file, line, rule violated, severity
  3. Suggestions: Improvements that aren't violations but would improve code quality

Weaknesses

  • Cannot run code or tests — only static analysis
  • May miss runtime type errors that mypy/pyright would catch
  • Cannot assess performance — only structural patterns
Changes

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.

  1. 2d ago First seen · 50 lines · 0 tokens per session scan A 64c7e337fa19

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository AlirezaSoltaniJazi/Skillnir (7 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 322 tokens. 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.