Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add goiltpatpat/patpat --skill patpat-architectgit clone --depth 1 https://github.com/goiltpatpat/patpatWrote 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.
[](https://agentmods.dev/skills/goiltpatpat/patpat/patpat-architect)<a href="https://agentmods.dev/skills/goiltpatpat/patpat/patpat-architect"><img src="https://agentmods.dev/badge/skills/goiltpatpat/patpat/patpat-architect/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.
<a href="https://agentmods.dev/skills/goiltpatpat/patpat/patpat-architect"><img src="https://agentmods.dev/badge/skills/goiltpatpat/patpat/patpat-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00038 | $0.00536 |
| Opus 5 | $0.00019 | $0.00268 |
| Sonnet 5 | $0.00008 | $0.00107 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
patpat-architect 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Patpat Architect
When invoked directly, read the operating protocol in full. Do not load the router.
Read repository truth, smallest safe change, and preserve safety. Apply the architecture change playbook.
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. 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 an observable experiment can settle a design fork, apply the prototype playbook. 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:
1. <step> -> verify: <targeted check or observation>
2. <step> -> verify: <targeted check or observation>
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.
- today Changed · +2 lines 8990f9bd90da
- 5d ago Changed 6e063df9863a
- 10d ago First seen · 30 lines · 38 tokens per session scan A a30fa67faca0
patpat-architect is a skill published in the GitHub repository goiltpatpat/patpat (1 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 536 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.
Other skills, from other repositories
Repository Knowledge Management
Create and maintain the Repository Knowledge Base using the official Agentic Engineering playbooks.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
requirements-authoring
To author, update, and validate functional/non-functional requirements as atomic units with user approval.
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
ijfw-workflow
Use when the user says: 'build', 'create', 'plan', 'new project', 'brainstorm', 'design', 'UI', 'website', 'dashboard', 'app', 'help me build', 'launch', 'book', 'campaign', or anything project-level. Skill body decides Quick vs Deep path.
ijfw-plan
Use when the user says 'plan this', 'plan it', 'make a plan', 'let's plan', 'draft a plan', 'how should we tackle this', 'break this down', or invokes '/ijfw-plan'. Produces a falsifiable PLAN.md (software, book, campaign, design, research) with task breakdown, dependency wave-table, and success criteria — gated by…