agentmods.dev

pytest.fix_local_tests

pytest.fix_local_tests is a skill for Claude Code from causify-ai/helpers. It costs 7 tokens per session (800 once invoked), scanned A, original, Apache-2.0.

A test-fixing task for failed local pytest tests. Pytest is a Python tool that runs automated tests; this task investigates the failure and changes the code to address its root cause.

In plain words
What is it for?
Running failed pytest tests, examining their code and output, identifying the cause, and fixing the implementation or test problem.
Why use it?
It removes the need to diagnose failing tests manually from scattered logs and source files. It checks the failure locally before applying a fix.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths.

not rated 150repo +3 yesterday A scan 7 tokens original Apache-2.0

Good fit Running failed pytest tests, examining their code and output, identifying the cause, and fixing the implementation or test problem.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/causify-ai/helpers/pytest.fix_local_tests
View source ↗ causify-ai/helpers causify.ai
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.

Any agent
npx skills add causify-ai/helpers --skill pytest.fix_local_tests
Clone the repo
git clone --depth 1 https://github.com/causify-ai/helpers

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 pytest.fix_local_tests

README.md
[![agentmods](https://agentmods.dev/badge/skills/causify-ai/helpers/pytest.fix_local_tests/github.svg)](https://agentmods.dev/skills/causify-ai/helpers/pytest.fix_local_tests)
Your own site
<a href="https://agentmods.dev/skills/causify-ai/helpers/pytest.fix_local_tests"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/pytest.fix_local_tests/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 pytest.fix_local_tests

Your own site · 80×15
<a href="https://agentmods.dev/skills/causify-ai/helpers/pytest.fix_local_tests"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/pytest.fix_local_tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 800 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 $0.00007 $0.00800
Opus 5.5 $0.00003 $0.00320
Sonnet 5.5 $0.00001 $0.00160
Haiku 4.5 $0.00001 $0.00080

Measured 3d ago against content hash 3a8e7aafeb5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pytest.fix_local_tests 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 3d 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/skills/pytest.fix_local_tests/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal

  • Given information about failed tests <FAILURE_INFO> run the tests, understand what is the root cause, and fix them

Workflow

Run Tests

  • The input <FAILURE_INFO> can be:

    • A failing test in pytest
      • E.g., dev_scripts_helpers/documentation/test/test_notes_to_pdf.py
    • A repro generated by pytest_failed_multi_build.py
      • E.g., tmp.pytest_failed_multi_build.repro.sh

  • Gather information about the failing tests by:

    • Reading the code
    • Inspecting the content of <FAILURE_INFO>
    • Running the tests locally, if needed
      • E.g., 
        > pytest_log `<FAILURE_INFO>`
> tmp.pytest_failed_multi_build.repro.sh

Analyze Failures

  • Read .claude/skills/pytest.rules.md about how to diagnose issues

  • Collect the failing tests from the run

    > i pytest_failed
...
Failed tests: 25/7
dev_scripts_helpers/documentation/test/test_notes_to_pdf.py::Test_notes_to_pdf_actions::test1
dev_scripts_helpers/documentation/test/test_notes_to_pdf.py::Test_notes_to_pdf_actions::test2
dev_scripts_helpers/documentation/test/test_notes_to_pdf.py::Test_notes_to_pdf_edge_cases::test1
dev_scripts_helpers/documentation/test/test_notes_to_pdf.py::Test_notes_to_pdf_edge_cases::test2
dev_scripts_helpers/documentation/test/test_notes_to_pdf.py::Test_notes_to_pdf_edge_cases::test3
dev_scripts_helpers/documentation/test/test_notes_to_pdf.py::Test_notes_to_pdf_edge_cases::test4
dev_scripts_helpers/documentation/test/test_notes_to_pdf.py::Test_notes_to_pdf_filters::test1
dev_scripts_helpers/documentation/test/test_notes_to_pdf.py::Test_notes_to_pdf_filters::test2
dev_scripts_helpers/documentation/test/test_notes_to_pdf.py::Test_notes_to_pdf_filters::test3
dev_scripts_helpers/documentation/test/test_notes_to_pdf.py::Test_notes_to_pdf_filters::test4
dev_scripts_helpers/documentation/test/test_notes_to_pdf.py::Test_notes_to_pdf_filters::test5
...
13:07:36 - WARN  lib_tasks_pytest.py pytest_failed:1745                 To run the failed tests run: tmp.pytest_failed.sh
...

Read the full file on GitHub · 79 lines

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. 3d ago First seen · 79 lines · 7 tokens per session scan A 3a8e7aafeb5f

Subscribe to this mod's changes

pytest.fix_local_tests is a skill published in the GitHub repository causify-ai/helpers (150 stars, last pushed yesterday), licensed Apache-2.0. It adds 7 tokens to every session and 800 once invoked, about $0.0000 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 2026-10-13.

DebuggingTestingUnit testing
Related

Other skills, from other repositories

testing

Skill validation framework PLUS daily test-suite health and regression intelligence. Validates skill conformance (frontmatter, manifest coverage, resolver coverage). Runs the project test suite in tiered phases (unit / evals / integration / system health), classifies failures, and produces a regression-aware report.

garrytan/gbrain · 63 tokens

verify

Verify that a change really works before you claim completion.

Yeachan-Heo/oh-my-claudecode · 12 tokens

detect-static-dependencies

ACTIVATION PREREQUISITE: the request or discovered target must explicitly identify C#, .NET, .cs, or .csproj; otherwise stay dormant without invoking this skill. USE FOR: locating System.DateTime.Now/UtcNow, System.IO.File/Directory, System.Environment, HttpClient, Console, or Process usage in C#; auditing C# code for…

dotnet/skills · 135 tokens

dart-downstream-fix

DART Downstream Fix: fix a DART bug reported through gz-physics or Gazebo.

dartsim/dart · 25 tokens

testing-blocks

Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.

adobe/skills · 61 tokens

experiment-iterative-coder

Iterative code refinement through plan → code → evaluate → refine cycles. Runs lint checks (ruff), tests (pytest), and structured self-evaluation each cycle, then diagnoses failures and refines. Decomposes complex tasks into sequential phases, iterates up to 3 times per phase (10 total). Use when: the main agent…

EvoScientist/EvoSkills · 145 tokens