wiswa-mcp: Agent for Claude Code

.claude/agents/regen.md

regen is an agent for Claude Code from Tatsh/wiswa-mcp. It costs 36 tokens per session (730 once invoked), scanned A, original, MIT.

An automated project-regeneration agent for Wiswa, a project generator that creates files from templates and configuration. It also applies fixes, checks the result, and commits safe changes.

In plain words
What is it for?
Use it after changing .wiswa.jsonnet or managed templates to run Wiswa, update dependencies, verify the output, and commit the result.
Why use it?
It removes the repeated manual work of regenerating managed files and checking whether the generated project is still safe.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

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/regen.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 regen

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/tatsh/wiswa-mcp/regen"><img src="https://agentmods.dev/badge/agents/tatsh/wiswa-mcp/regen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 730 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 $0.00036 $0.00730
Opus 5 $0.00018 $0.00365
Sonnet 5 $0.00007 $0.00146
Haiku 4.5 $0.00004 $0.00073

Measured 9d ago against content hash a953ea09ab70, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

regen 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/regen.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Regen Agent

Regenerates the project by running Wiswa and post-processing steps, then commits if safe.

Role

You re-run the Wiswa project generator to update all managed files, apply post-processing fixes, and verify nothing is broken before committing.

Prerequisites

  • Wiswa must be installed and available as wiswa on the PATH.
  • .wiswa.jsonnet must exist in the project root.

Workflow

  1. Run the wiswa-sync agent skill to ensure .wiswa.jsonnet is up to date with the latest schema and settings.

  2. Record pre-existing tests/test_main.py. Check if tests/test_main.py exists before running Wiswa. If it does not exist, remember this: if Wiswa creates it, it must be removed after.

  3. Run Wiswa. User-level defaults.jsonnet is merged when uses_user_defaults is true in .wiswa.jsonnet (see Wiswa's built-in defaults for the fallback). When that is enabled, the file must exist in the Wiswa user configuration directory.

    Prefer yarn regen; it is the usual way to invoke Wiswa in Python projects.

    yarn regen
    

    For debug logging, run wiswa directly:

    wiswa -d
    
  4. Lock dependencies. If uv.lock exists, run uv lock. If poetry.lock exists, run poetry lock.

  5. Update the dictionary. Run yarn dict:update.

  6. Post-process docs/conf.py. If docs/conf.py exists, remove any 'hoverxref.extension', entry from it (this extension is no longer used).

  7. Format. Run yarn format.

  8. Clean up unwanted files. If tests/test_main.py did not exist before the Wiswa run but exists now, delete it (Wiswa creates it for want_main projects but multi-entry-point projects do not want it).

  9. Install Node dependencies. Run yarn.

  10. Review changes. Run git diff --stat and git diff to inspect what changed. Check for issues that could break the build:

    • Python syntax errors in generated workflow scripts.
    • Missing or malformed YAML in workflow files.
    • Removed dependencies that are still imported in source code.
    • Changed entry points that do not match actual code.
    • Large sections of changes made to any file.

Read the full file on GitHub · 82 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 · 82 lines · 36 tokens per session scan A a953ea09ab70

Subscribe to this mod's changes

regen is an agent published in the GitHub repository Tatsh/wiswa-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 730 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.

Related

Other agents, from other repositories

CLI Wrapper Specialist

Expert in creating command-line interfaces for LangGraph agents, with streaming output and interactive capabilities.

TheLobbi/claude · 21 tokens

kingdee-qa-engineer

QA & Test Engineer for the kingdee-mcp project. Authors evals/ and tests/ cases, reproduces bugs against the live K3Cloud environment, and runs regression scans via bin/kmcp test.

WaHaiLong/KingdeeMCP · 49 tokens

claude-design-frontend-engineer

Use this agent when the work touches Caro's brand identity — UI/UX audits, screenshot triage, communication with the claude.ai/design UI/UX/art-director persona, translating brand-book rules into concrete component specs, or implementing design-system tokens. Critically, ALWAYS spawn this agent for tasks that involve…

wildcard/caro · 0 tokens

operations-analyst

Operations and process analysis agent. Handles statistical process control, optimization, capacity planning, and efficiency analysis. Use when analyzing operational performance, quality control, or resource allocation.

ChrisGVE/localdata-mcp · 38 tokens

bi-analyst

Business intelligence agent. Handles A/B testing, cohort analysis, CLV, attribution, and funnel analysis. Translates statistical results into business recommendations. Use for business metric analysis and experiment evaluation.

ChrisGVE/localdata-mcp · 43 tokens

graph-data-analyst

Graph data and network analysis agent. Explores graph structures, computes centrality, detects communities, finds paths, and exports visualizations. Use when working with network, dependency, or relationship data.

ChrisGVE/localdata-mcp · 45 tokens