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 commands/ruslan-korneev/claude-plugins/typecheckgit clone --depth 1 https://github.com/ruslan-korneev/claude-pluginsWhat 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 | $0.00016 | $0.00551 |
| Opus 5 | $0.00008 | $0.00275 |
| Sonnet 5 | $0.00003 | $0.00110 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
typecheck 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
Command /types:check
Run type checking and show errors with explanations.
Instructions
Step 1: Determine the tool
Check for configuration:
# mypy
test -f pyproject.toml && grep -q "tool.mypy" pyproject.toml && echo "mypy configured"
# pyright
test -f pyrightconfig.json && echo "pyright configured"
Step 2: Run the check
# mypy
mypy {{ path | default: "src/" }} --show-error-codes
# pyright
pyright {{ path | default: "src/" }}
Step 3: Group errors
Error categories:
- Missing return type — no return type annotation
- Incompatible types — incompatible types in assignment/call
- Missing type annotation — no annotation for variable
- Optional handling — working with Optional without None check
- Generics — errors with generic types
Step 4: Show solutions
For each error show:
- What the error means
- How to fix it WITHOUT
type: ignore
NEVER SUGGEST
# NEVER:
result = some_function() # type: ignore
value: Any = something # Avoid Any
cast(SomeType, value) # Only if there's no other way
Response Format
## Type Checking Results
### Tool: mypy
### Path: {{ path }}
### Errors found: X
#### Missing return type (N)
- `src/services/user.py:45` — `def process()` → add `-> None` or specific type
#### Incompatible types (N)
- `src/repositories/order.py:23` — `str` vs `int` → convert types explicitly
#### Optional handling (N)
- `src/api/routes.py:67` — possible `None` → add check `if value is not None`
### How to Fix
1. Add return type annotations to functions without them
2. Use `if x is not None` instead of `cast` or `type: ignore`
3. Replace `Any` with specific types or `TypeVar`
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 · 93 lines · 16 tokens per session scan A 73fdeb44fb4e
typecheck is a command published in the GitHub repository ruslan-korneev/claude-plugins (4 stars, last pushed 6mo ago), licensed MIT. It adds 16 tokens to every session and 551 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 commands, from other repositories
validate_changed_docstrings
Validates Python docstrings in all uncommitted changed files using Sphinx parsing.
implement-python
Senior Python engineer implementation command. Launches a background agent with full Python development capabilities and access to the mastering-python-skill reference materials.
execute-pydantic-ai-prp
Implement a Pydantic AI agent using the PRP file.
run
Command "run" from ErisPulse/ErisPulse, covering erispulse.cli.commands.run 模块, 模块概述, 类列表, class reloadhandler(filesystemeventhandler) and class runcommand(command).
scaffold
Scaffold a new Python/PySide6 application with pyproject.toml, src layout, and qt-suite config.
prepare-dataset
Analyse a raw data file (CSV, JSON, JSONL, TSV, Parquet) and generate a complete Python script scripts/dataset/ .py that inherits from BaseDatasetPreparer and transforms the file into a JSONL dataset ready for fine-tuning with Unsloth.