Skip to content
Agentmart
Submit a tool

patpat-architect

Design repository-native changes before implementation or run a requested read-only architecture-opportunity scan.

Skill by goiltpatpat

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying patpat-architect?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/goiltpatpat-patpat-architect

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Design repository-native changes before implementation or run a requested read-only architecture-opportunity scan. Use for architecture, migrations, public contracts, security-sensitive boundaries, cross-cutting work, or decisions with meaningful compatibility risk.

Use cases: design, security

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/patpat-architect

What's inside

Skill name
patpat-architect
Description
Design repository-native changes before implementation or run a requested read-only architecture-opportunity scan. Use for architecture, migrations, public contracts, security-sensitive boundaries, cross-cutting work, or decisions with meaningful compatibility risk.
License
MIT
Metadata
patpat.ontology: {"schema":"patpat-ontology/v1","mutation_level":"READ_ONLY","target_entity":"Codebase","requires_state":[],"produces_state":[],"verification_cmd":""}
Instructions
32 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Patpat Architect

Before following this skill, apply the [skill state and mutation gate](../patpat-loop/references/operating-protocol.md#skill-state-and-mutation-gate).

When invoked directly, read the [operating protocol](../patpat-loop/references/operating-protocol.md) in full. Do not load the router.

Read [repository truth](../patpat-loop/principles/repository-truth.md), [smallest safe change](../patpat-loop/principles/smallest-safe-change.md), [preserve safety](../patpat-loop/principles/preserve-safety.md), [subtract before you add](../patpat-loop/principles/subtract-before-you-add.md), [attack the premise](../patpat-loop/principles/attack-the-premise.md), and [redesign from first principles](../patpat-loop/principles/redesign-from-first-principles.md). Apply the [architecture change playbook](../patpat-loop/playbooks/architecture-change.md).

Ground the design in current repository evidence. Name the contract, its callers, the changed behavior, migration impact, compatibility risk, rollback path, and proof contract.

For a material architecture decision or a change that crosses a meaningful boundary, the architecture output must include a compact caller usage sketch, the core data or type shape, boundary-relevant signatures, failure modes, rejected alternatives, and the proof that will show implementation still preserves the chosen shape. If implementation needs an unplanned parameter, state escape hatch, or compatibility path, stop and revisit the sketch before adding a workaround. Keep smaller local changes on the bounded-change path.

Prefer a design that reduces degrees of freedom and reuses repository structure. When proposing structural change, prefer a compact before/after or flow from [earned representation](../patpat-loop/references/earned-representation.md). Seek independent review before implementing auth, billing, permissions, destructive migrations, production infrastructure, or public contract changes. Stop for explicit approval when required.

Keep architecture work read-only by default. Do not edit implementation files. When the user also requested implementation, finish the design gate and hand the authorized unit to `patpat-change` under `patpat-loop` instead of implementing inside this workflow.

When the user asks what architecture should improve rather than asking to design a known change, run the bounded discovery route in the [architecture change playbook](../patpat-loop/playbooks/architecture-change.md). Return no more than three source-backed candidates with current friction, proposed boundary, test payoff, and confidence. Stop for the user to choose before design or implementation. Do not make this scan an automatic prelude to every architecture request.

When an observable experiment can settle a design fork, apply the [prototype playbook](../patpat-loop/playbooks/prototype.md). Keep prototypes in an isolated scratch area outside production paths and treat them as disposable evidence, not implementation.

Produce a concise sequence in this form:

```text
1. <step> -> verify: <targeted check or observation>
2. <step> -> verify: <targeted check or observation>
```

## Placement and layering heuristics

Structure new code and boundary refactors into explicit, unidirectional layers:
- **Domain Core**: Pure domain entities, state-machine transitions, and core invariants. No dependencies on external frameworks, transports, or I/O.
- **Application Services**: Use cases, command dispatchers, orchestration graphs, and coordination logic.
- **Adapters**: Concrete implementations of boundary interfaces—CLI parsers, HTTP/API clients, disk storage, and external providers.

Never leak adapter concerns into the domain core. Dependencies point inward toward the core.

## Mutation boundary

Remain read-only with respect to repository implementation and external delivery. Limit incidental verifier artifacts to the declared proof contract, clean them up, and hand any authorized mutation back to `patpat-loop`.

From goiltpatpat/patpat, MIT.

More from goiltpatpat/patpat

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Oct 14, 2026 (16 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from goiltpatpat

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get patpat-architect running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying patpat-architect?

CallGet help
Cite this page

patpat-architect skill. Agent Mart. https://agentmart.dev/skills/goiltpatpat-patpat-architect (last updated 2026-10-24)