wiswa-mcp: Agent for Claude Code

.claude/agents/coverage-improver.md

coverage-improver is an agent for Claude Code from Tatsh/wiswa-mcp. It costs 34 tokens per session (407 once invoked), scanned A, original, MIT.

A coding agent that finds untested code paths and writes focused pytest tests. Test coverage measures which parts of a program's code tests exercise.

In plain words
What is it for?
Use it to inspect missing lines and branches, add tests for those paths, rerun coverage, and pass resulting style issues to a fixer.
Why use it?
It helps close meaningful coverage gaps before a release or when coverage drops below the project target.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is Tatsh/wiswa-mcp's own configuration. It tells Claude Code how to work on wiswa-mcp 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 wiswa-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Tatsh/wiswa-mcp. 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/Tatsh/wiswa-mcp/master/.claude/agents/coverage-improver.md
Clone the repo
git clone --depth 1 https://github.com/Tatsh/wiswa-mcp

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 coverage-improver

README.md
[![agentmods](https://agentmods.dev/badge/agents/tatsh/wiswa-mcp/coverage-improver.svg)](https://agentmods.dev/agents/tatsh/wiswa-mcp/coverage-improver)
Your own site
<a href="https://agentmods.dev/agents/tatsh/wiswa-mcp/coverage-improver"><img src="https://agentmods.dev/badge/agents/tatsh/wiswa-mcp/coverage-improver.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 407 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 $0.00034 $0.00407
Opus 5 $0.00017 $0.00204
Sonnet 5 $0.00007 $0.00081
Haiku 4.5 $0.00003 $0.00041

Measured 6d ago against content hash 6dc950f88f72, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

coverage-improver 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 6d 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/coverage-improver.md · 40 lines

What it actually says

Coverage Improver Agent

Identifies test coverage gaps and writes tests to fill them.

Role

You improve test coverage by finding uncovered code and writing targeted tests. Follow all conventions in .claude/rules/python-tests.md and the test-writing patterns defined in .claude/agents/test-writer.md.

Workflow

  1. Run uv run pytest --cov wiswa.mcp --cov-branch --cov-report term-missing:skip-covered to get the current coverage report.
  2. Parse the output to find files with missing lines/branches.
  3. For each uncovered section: a. Read the source file to understand what the uncovered code does. b. Read the existing test file for patterns and style. c. Write tests that exercise the uncovered paths.
  4. Run uv run pytest --cov wiswa.mcp --cov-branch --cov-report term-missing:skip-covered again to verify coverage improved.
  5. Launch the qa-fixer agent to format and fix any lint/spelling issues.

Guidelines

  • Focus on uncovered branches and lines, not just line count.
  • Audit # pragma: no cover comments - remove if the code can reasonably be tested.
  • Keep # pragma: no cover for genuinely untestable code (e.g. platform-specific guards that cannot run in CI, interactive UI code).
  • Follow the project's test patterns: CliRunner for commands, mocker.patch for complex mocks, monkeypatch.setattr for simple replacements.
  • All fixtures in conftest.py, no docstrings on tests, type hints on everything.
  • Prefer parametrised tests to cover multiple branches in one test function.
  • Test both success and error paths.
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. 6d ago First seen · 40 lines · 34 tokens per session scan A 6dc950f88f72

Subscribe to this mod's changes

coverage-improver is an agent published in the GitHub repository Tatsh/wiswa-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 407 once invoked, about $0.0002 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.