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 andreaswasita/copilot-agents-dojo --skill architecture-sketchinggit clone --depth 1 https://github.com/andreaswasita/copilot-agents-dojoWrote 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/andreaswasita/copilot-agents-dojo/architecture-sketching)<a href="https://agentmods.dev/skills/andreaswasita/copilot-agents-dojo/architecture-sketching"><img src="https://agentmods.dev/badge/skills/andreaswasita/copilot-agents-dojo/architecture-sketching/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/andreaswasita/copilot-agents-dojo/architecture-sketching"><img src="https://agentmods.dev/badge/skills/andreaswasita/copilot-agents-dojo/architecture-sketching.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 | $0.00012 | $0.01541 |
| Opus 5 | $0.00006 | $0.00771 |
| Sonnet 5 | $0.00002 | $0.00308 |
| Haiku 4.5 | $0.00001 | $0.00154 |
Grade A, and why
architecture-sketching 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Sketching Skill
Defines the data shapes, public signatures, module ownership, alternatives, and invalidation conditions for a cross-boundary change before implementation begins. It produces a small design contract that implementation can test and revise. It does NOT require architecture ceremony for a local change with an obvious existing pattern.
This workflow adapts architecture-exploration ideas from Lauren Tan's pstack project, licensed under MIT, to the dojo's verification and traceability model.
When to Use
- A change crosses a function, module, service, process, or persistence boundary.
- A new API, event, command, schema, or shared type is being introduced.
- Several credible designs exist and choosing one would be expensive to reverse.
- Implementation keeps adding casts, optional fields, locks, wrappers, or special cases.
- The user asks to architect, design, model, or decide where behavior belongs.
- NOT for a one-file change that follows a clear local pattern without changing a contract.
Prerequisites
- An approved problem statement or requirements package.
- A grounded view of affected code from
view,grep,glob, orcodebase-onboarding. plan-before-codeactive for multi-step work.subagent-strategyavailable when competitive design exploration is justified.- A writable design location chosen by repository convention.
How to Run
1. Ground the current flow, constraints, and ownership.
2. Name the data shapes and illegal states.
3. Sketch public signatures and module boundaries with no implementation.
4. Compare credible alternatives and select one with a written rationale.
5. Define verification and explicit signals that would invalidate the sketch.
6. Implement against the sketch; redesign when repeated friction disproves it.
Quick Reference
| Artifact | Required content |
|---|---|
| Problem frame | Goal, scope, constraints, and success predicate |
| Data shapes | Inputs, outputs, state, identity, ownership, invalid states |
| Contract sketch | Public types, signatures, commands, events, or endpoints |
| Module map | Which component owns each decision and dependency direction |
| Alternatives | Two or three credible shapes, or why only one is viable |
| Selection rationale | Tradeoff that decided the shape and what was rejected |
| Verification plan | Static checks plus real-artifact behavior |
| Invalidation signals | Evidence that requires redesign instead of another patch |
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.
- 3d ago First seen · 174 lines · 12 tokens per session scan A e9d9ff256054
architecture-sketching is a skill published in the GitHub repository andreaswasita/copilot-agents-dojo (53 stars, last pushed 4d ago), licensed MIT. It adds 12 tokens to every session and 1,541 once invoked, about $0.0001 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 2026-09-07.
Other skills, from other repositories
php
Use when writing, reviewing or modernizing PHP (8.3-8.5) outside Laravel — strict types, union and intersection types, readonly classes, backed enums, property hooks and asymmetric visibility, the pipe operator and clone-with, Composer with PSR-4, PER-CS style, PSR interop, and the quality toolchain (PHPStan, Pint…
codebase-onboarding
Use when you land in an unfamiliar or inherited codebase and must get productive fast: a breadth-first map of entry points, request flow, module ownership, hidden side effects (cron, webhooks, workers) and churn hotspots, committed as CODEBASE-MAP.md. NOT a deep audit of one module (that is analyze) or chasing one…
decision-ledger
A session record for tracking unresolved decisions and drafting them into `.governance/claims/` when they are settled. It preserves both the decision and the reason behind it.
governance-bootstrap
A guided checklist for creating a project's governance system from scratch when no governance exists.
session-grounding
A session-start procedure for checking the current facts, scope, and work track in a governed project before taking action.
truth-first
A set of rules for writing technical conclusions and performing irreversible or state-changing operations. It requires evidence tied to file and line locations and restricts unsupported claims.