just-works: Agent for Claude Code

.claude/agents/python-code-writer.md

python-code-writer is an agent for Claude Code from Dynokostya/just-works. It costs 50 tokens per session (272 once invoked), scanned A, original, Apache-2.0.

A Python coding agent that writes and edits Python files according to a project's existing standards, then checks the affected code with Ruff and mypy.

In plain words
What is it for?
Use it for focused Python implementation or editing tasks that require project-specific checks.
Why use it?
It reduces inconsistent style and catches common linting and type errors while changes are being made.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is Dynokostya/just-works's own configuration. It tells Claude Code how to work on just-works itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything just-works configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Dynokostya/just-works. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Dynokostya/just-works/main/.claude/agents/python-code-writer.md
Clone the repo
git clone --depth 1 https://github.com/Dynokostya/just-works

Made for: Claude Code.

Wrote 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.

agentmods badge for python-code-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/dynokostya/just-works/python-code-writer/github.svg)](https://agentmods.dev/agents/dynokostya/just-works/python-code-writer)
Your own site
<a href="https://agentmods.dev/agents/dynokostya/just-works/python-code-writer"><img src="https://agentmods.dev/badge/agents/dynokostya/just-works/python-code-writer/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.

agentmods 80×15 button for python-code-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/dynokostya/just-works/python-code-writer"><img src="https://agentmods.dev/badge/agents/dynokostya/just-works/python-code-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 272 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00050 $0.00272
Opus 5.5 $0.00020 $0.00109
Sonnet 5.5 $0.00010 $0.00054
Haiku 4.5 $0.00005 $0.00027

Measured 9d ago against content hash 0e6d906c1ec7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

python-code-writer 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 9d 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.

.claude/agents/python-code-writer.md · 25 lines

What it actually says

Write clean, type-safe Python following project standards.

Before Writing

Read the files you will change before making edits. For single-file edits, reading the target file is sufficient. For cross-cutting changes, read the directly affected modules. Check pyproject.toml for Python version, ruff/mypy configuration, and dependencies.

When adding or changing HTTP API endpoints, load the rest-api skill with the Skill tool.

Quality

Write code that passes the project's linter, formatter, and type checker. After editing, discover them from project config (pyproject.toml, ruff.toml, mypy.ini) and run ruff on the affected files, plus mypy only if the project configures it, unless a project hook already does it.

Report

End with a short report: files changed, checks run with their results, checks skipped and why, and assumptions made.

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. 9d ago Changed · +20 tokens per session 0e6d906c1ec7
  2. 17d ago Changed · -6 lines · +4 tokens per session 729c14e5de7f
  3. 1mo ago Changed · -1 lines 6268b2e6b172
  4. 2mo ago First seen · 32 lines · 26 tokens per session scan A 4293af7ed06b

Subscribe to this mod's changes

python-code-writer is an agent published in the GitHub repository Dynokostya/just-works (14 stars, last pushed 10d ago), licensed Apache-2.0. It adds 50 tokens to every session and 272 once invoked, about $0.0002 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 2026-09-04.

Related

python-code-writer compared with agents from other repositories

python-code-writer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
python-code-writerDynokostya/just-worksAgent1410d agoApache-2.0A50Claude Code
Geoprocessing SpecialistSHAdd0WTAka/Zen-Ai-PentestAgent5033d agoMITA45Claude Code, OpenCode
python-proechoVic/blade-codeAgent18124d agoMITA51Claude Code
temporal-test-buildercanonical/copilot-collectionsAgent323d agoApache-2.0A56Claude Code
package-revieweroborchers/fractional-ctoAgent3612d agoMITA287Claude Code
script-operatorMadGraphTeam/MadAgentsAgent153mo agoMITA24Claude Code
python-reviewerFmarzochi/EGCAgent68yesterdayApache-2.0A43Claude Code, Kiro