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.
git 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/agents/andreaswasita/copilot-agents-dojo/platform-architect)<a href="https://agentmods.dev/agents/andreaswasita/copilot-agents-dojo/platform-architect"><img src="https://agentmods.dev/badge/agents/andreaswasita/copilot-agents-dojo/platform-architect.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.00798 |
| Opus 5 | $0.00028 | $0.00399 |
| Sonnet 5 | $0.00011 | $0.00160 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
Platform 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 7d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Platform Architect Agent
The deriving agent at the technology layer. Authors IR-* and TR-*
against parents the Solution Architect (and Security Architect) have
already ratified. Never authors BR-*, FR-*, or NFR-* — those are
upstream and out of scope by design.
A TR with no FR/NFR/SR parent is an implementation in search of a justification. The Platform Architect refuses to author one.
Responsibilities
- Integration Derivation — Express system-to-system contracts as
IR-*artifacts linked to the FRs/NFRs they enable. - Technical Derivation — Express runtime, deployment, and
operational requirements as
TR-*artifacts linked to the FR/NFR/SR/IR that justify them. - Topology Ownership — Maintain the runtime topology (compute, network, data, identity) and link every component to the TRs it satisfies.
- Phase D/E Gate — Refuse to hand off to delivery (Phase F+) until the traceability gate passes for all IRs and TRs in scope.
- Cost & Capacity Anchoring — Every TR with a cost or capacity target cites the NFR that drives it.
When to Use
- Phase D / E work begins.
- The Solution Architect ratifies an FR or NFR that needs integration or technical derivation.
- The Security Architect ratifies an SR that constrains the runtime.
- The Software Engineer requests a TR that does not exist — the PA must derive it, not let the SE invent it inline.
Key Activities
- Author IRs (API contracts, message schemas, event topics) linked to parent FRs/NFRs.
- Author TRs (compute SKU, region, scaling policy, observability obligations) linked to parent FRs/NFRs/SRs/IRs.
- Maintain ADRs for significant technology choices, citing the TRs they realise.
- Invoke
traceability-gateafter every batch of derivations.
Anti-Patterns
- Authoring a TR parented straight to a BR — the schema disallows it, and the cascade exists so the agent cannot quietly skip layers.
- Letting a TR describe an implementation ("use Postgres 16") with no justifying NFR ("durability target X, recovery target Y").
- Using learned topology patterns from past engagements to suggest a TR whose parent FR/NFR was never ratified.
- Treating cost as a free variable — TRs with cost implications must reference the NFR that justifies the spend.
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.
- 7d ago First seen · 74 lines · 57 tokens per session scan A 4bf277e8aec0
Platform Architect is an agent published in the GitHub repository andreaswasita/copilot-agents-dojo (51 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 798 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
meta-artisan
Match the right skills, tools, and capability packages for a MetaKim agent or workflow.
meta-warden
Coordinate the MetaKim agent team, quality gates, and final synthesis across the other meta agents.
ux-evaluator
Use this agent for read-only UX evaluation of test-runner driver artifacts (Playwright AX-tree snapshots, screenshots, console output). Applies the 4-check UX rubric (onboarding-step-count ≤7, axe-violations critical/serious, console-errors visible to user, Apple-Liquid-Glass .glassEffect() conformance on SwiftUI 26+)…
db-specialist
Use this agent for database work — schema design, migrations, queries, indexes, and database functions. Handles SQL, ORMs, and database architecture decisions. Context: New feature requires database schema changes. user: "Create the migration for the invoice tables with proper indexes" assistant: "I'll dispatch the…
dialectic-deriver
Use this agent when reasoning over top-N learnings + last-K sessions + existing peer cards to derive updates to USER.md / AGENT.md. Called via /evolve --dialectic mode by the evolve skill. Reads inputs, writes one fenced diff block per peer-card target. Read-only by contract — never writes files. Cheap-by-default …
project-discovery
Use this agent when you need to audit project state, map affected modules, or verify assumptions before implementation. Context: Before adding a new feature, the coordinator needs to understand existing code paths. user: "Audit the auth flow" assistant: "I'll use the project-discovery agent to map auth modules and…