wiswa-mcp: Skill for Claude Code

.claude/skills/ci/SKILL.md

ci is a skill for Claude Code from Tatsh/wiswa-mcp. It costs 0 tokens per session (2,001 once invoked), scanned A, original, MIT.

A workflow for creating high-quality Git commits from pending code changes. It checks the changes, reviews relevant files with specialist checks, and follows the repository's recent commit style.

In plain words
What is it for?
Use it when preparing a commit, especially when Python files or command-line interface files are among the changes.
Why use it?
It reduces the chance of committing unrelated files or overlooking checks that apply to the code you changed.

Skill 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/skills/ci/SKILL.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 ci

README.md
[![agentmods](https://agentmods.dev/badge/skills/tatsh/wiswa-mcp/ci/github.svg)](https://agentmods.dev/skills/tatsh/wiswa-mcp/ci)
Your own site
<a href="https://agentmods.dev/skills/tatsh/wiswa-mcp/ci"><img src="https://agentmods.dev/badge/skills/tatsh/wiswa-mcp/ci/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 ci

Your own site · 80×15
<a href="https://agentmods.dev/skills/tatsh/wiswa-mcp/ci"><img src="https://agentmods.dev/badge/skills/tatsh/wiswa-mcp/ci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,001 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 $0.00000 $0.02001
Opus 5 $0.00000 $0.01001
Sonnet 5 $0.00000 $0.00400
Haiku 4.5 $0.00000 $0.00200

Measured 9d ago against content hash 5d1a505edd1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ci 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/skills/ci/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit

Create high-quality Git commits for all pending changes.

Gathering context

Run these in parallel:

  1. git diff - unstaged changes.
  2. git diff --cached - staged changes.
  3. git status - untracked files and overall state.
  4. git log --no-merges --format='%s%n%b---' -20 | grep -v '^bump:' | grep -iv dependabot - recent commit message style examples.

Running agents

After gathering context but before committing, determine which agents to run based on the changed files. Launch each agent sequentially using the Agent tool with subagent_type general-purpose, telling it to follow the corresponding .claude/agents/<name>.md file. Scope each agent to only the changed files, not the entire project.

You must skip any agents that are not relevant to the changed files (e.g. if no Click command files changed, skip the click-auditor).

When Python code is being committed

If any changed files are under wiswa/mcp/ or tests/, run the following agents in order:

  1. python-moderniser - upgrade to modern Python features.
  2. click-auditor - validate Click command consistency. Only run if files under wiswa/mcp/commands/ changed.
  3. docstring-fixer - fix missing or incomplete docstrings.
  4. copy-editor - fix prose in comments, docstrings, and strings.
  5. test-writer - generate/update tests for new/changed code. Skip if the only changes are in tests/.
  6. qa-fixer - format and fix lint/spelling issues.

When user-facing changes are being committed

  • changelog - update CHANGELOG.md only for user-facing changes (behaviour, CLI, public API, security, or meaningful dependency constraints that affect installs). After it completes, check if CHANGELOG.md was modified (git diff CHANGELOG.md). If it was, stage it with the relevant commit. Follow .claude/agents/changelog.md, including its skip list.

    Files under wiswa/mcp/, tests/, or version changes in pyproject.toml are candidates for the changelog agent only when they change what users see or how the software behaves. Editing those paths is not sufficient on its own.

Read the full file on GitHub · 182 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. 9d ago First seen · 182 lines · 0 tokens per session scan A 5d1a505edd1d

Subscribe to this mod's changes

ci is a skill published in the GitHub repository Tatsh/wiswa-mcp (0 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,001 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.