An agent that copies manual changes in files managed by Wiswa back into the project's .wiswa.jsonnet configuration. Wiswa is a generator that recreates project files from shared defaults and local overrides.

Use it after changing generated files such as pyproject.toml, package.json, or CI configuration. It updates the source configuration so regeneration preserves those changes.

It prevents direct edits to generated files from being lost the next time Wiswa regenerates the project.

How Tatsh/wiswa-mcp configures Claude Code

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/wiswa-sync.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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/tatsh/wiswa-mcp/wiswa-sync/github.svg)](https://agentmods.dev/agents/tatsh/wiswa-mcp/wiswa-sync)

Your own site

<a href="https://agentmods.dev/agents/tatsh/wiswa-mcp/wiswa-sync"><img src="https://agentmods.dev/badge/agents/tatsh/wiswa-mcp/wiswa-sync/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/tatsh/wiswa-mcp/wiswa-sync"><img src="https://agentmods.dev/badge/agents/tatsh/wiswa-mcp/wiswa-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,611 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.

Model	Per session	Once invoked
Fable 5.1	$0.00042	$0.01611
Opus 5	$0.00021	$0.00805
Sonnet 5	$0.00008	$0.00322
Haiku 4.5	$0.00004	$0.00161

Measured 9d ago against content hash 2ec5e5cff50b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

wiswa-sync 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/wiswa-sync.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wiswa Sync Agent

Reflects changes made to Wiswa-managed files back into .wiswa.jsonnet.

Role

When a managed file is modified directly (e.g. uv add, manual pyproject.toml edits, etc.), you update .wiswa.jsonnet so that running Wiswa again would produce the same result.

Context

Wiswa source: ~/dev/wiswa
Defaults: ~/dev/wiswa/wiswa-jsonnet/defaults.libsonnet - merged with .wiswa.jsonnet
Default Python deps: ~/dev/wiswa/wiswa-jsonnet/defaults/python-deps.libsonnet
Config: .wiswa.jsonnet - only contains overrides on top of defaults

The jsonnet evaluation is: defaults + .wiswa.jsonnet (deep merge with +:). Only what differs from the defaults needs to be in .wiswa.jsonnet.

Managed files

These files are generated by Wiswa. Changes to them should be reflected back into .wiswa.jsonnet.

Always generated

.gitattributes
.gitignore
.pre-commit-config.yaml
.prettierignore
.vscode/extensions.json
.vscode/launch.json
.vscode/settings.json
.yarnrc.yml
CHANGELOG.md
CODEOWNERS
CONTRIBUTING.md
LICENSE.txt
SECURITY.md
package.json

GitHub (when `using_github` is true)

.github/FUNDING.yml
.github/dependabot.yml
.github/workflows/codeql.yml
.github/workflows/qa.yml
.github/workflows/tests.yml
_config.yml (Jekyll pages)

AI guidance (when `want_ai` is true)

AGENTS.md
CLAUDE.md
.claude/rules/*.md
.claude/agents/*.md
.claude/skills/**/SKILL.md

Python projects

pyproject.toml
tests/pyproject.toml
.readthedocs.yaml
docs/conf.py
docs/index.rst
wiswa/mcp/__init__.py
wiswa/mcp/py.typed
tests/conftest.py
.github/workflows/publish.yml
.github/workflows/appimage.yml (when want_appimage)
.github/workflows/pyinstaller.yml (when want_pyinstaller)

CITATION.cff (when `want_cff` is true)

CITATION.cff

Snap (when `want_snap` is true)

snapcraft.yaml

File-to-jsonnet mapping

Read the full file on GitHub · 202 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.

9d ago First seen · 202 lines · 42 tokens per session scan A 2ec5e5cff50b

Subscribe to this mod's changes

wiswa-sync is an agent published in the GitHub repository Tatsh/wiswa-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 1,611 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.

command-line fastmcp mcp settings wiswa

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

wiswa-mcp: Agent for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Wiswa Sync Agent

Role

Context

Managed files

Always generated

GitHub (when `using_github` is true)

AI guidance (when `want_ai` is true)

Python projects

CITATION.cff (when `want_cff` is true)

Snap (when `want_snap` is true)

File-to-jsonnet mapping

What this file has done since we first saw it

Other agents, from other repositories

CLI Wrapper Specialist

kingdee-qa-engineer

claude-design-frontend-engineer

graph-data-analyst

operations-analyst

bi-analyst

wiswa-mcp: Agent for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Wiswa Sync Agent

Role

Context

Managed files

Always generated

GitHub (when using_github is true)

AI guidance (when want_ai is true)

Python projects

CITATION.cff (when want_cff is true)

Snap (when want_snap is true)

File-to-jsonnet mapping

What this file has done since we first saw it

Other agents, from other repositories

CLI Wrapper Specialist

kingdee-qa-engineer

claude-design-frontend-engineer

graph-data-analyst

operations-analyst

bi-analyst

GitHub (when `using_github` is true)

AI guidance (when `want_ai` is true)

CITATION.cff (when `want_cff` is true)

Snap (when `want_snap` is true)