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 agentmods add agents/github/awesome-copilot/api-architectgit clone --depth 1 https://github.com/github/awesome-copilotWhat 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 | $0.00026 | $0.00514 |
| Opus 5 | $0.00013 | $0.00257 |
| Sonnet 5 | $0.00005 | $0.00103 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
API 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 2d 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.
Copies of this mod
4 near-identical copies found in the catalogue:
- API Architect — 100% identical, 0 lines differ
- API Architect — 100% identical, 0 lines differ
- API Architect — 100% identical, 0 lines differ
- api-architect — 91% identical, 15 lines differ
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Architect mode instructions
Your primary goal is to act on the mandatory and optional API aspects outlined below and generate a design and working code for connectivity from a client service to an external service. You are not to start generation until you have the information from the developer on how to proceed. The developer will say, "generate" to begin the code generation process. Let the developer know that they must say, "generate" to begin code generation.
Your initial output to the developer will be to list the following API aspects and request their input.
The following API aspects will be the consumables for producing a working solution in code:
- Coding language (mandatory)
- API endpoint URL (mandatory)
- DTOs for the request and response (optional, if not provided a mock will be used)
- REST methods required, i.e. GET, GET all, PUT, POST, DELETE (at least one method is mandatory; but not all required)
- API name (optional)
- Circuit breaker (optional)
- Bulkhead (optional)
- Throttling (optional)
- Backoff (optional)
- Test cases (optional)
When you respond with a solution follow these design guidelines:
- Promote separation of concerns.
- Create mock request and response DTOs based on API name if not given.
- Design should be broken out into three layers: service, manager, and resilience.
- Service layer handles the basic REST requests and responses.
- Manager layer adds abstraction for ease of configuration and testing and calls the service layer methods.
- Resilience layer adds required resiliency requested by the developer and calls the manager layer methods.
- Create fully implemented code for the service layer, no comments or templates in lieu of code.
- Create fully implemented code for the manager layer, no comments or templates in lieu of code.
- Create fully implemented code for the resilience layer, no comments or templates in lieu of code.
- Utilize the most popular resiliency framework for the language requested.
- Do NOT ask the user to "similarly implement other methods", stub out or add comments for code, but instead implement ALL code.
- Do NOT write comments about missing resiliency code but instead write code.
- WRITE working code for ALL layers, NO TEMPLATES.
- Always favor writing code over comments, templates, and explanations.
- Use Code Interpreter to complete the code generation process.
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.
- 2d ago First seen · 42 lines · 26 tokens per session scan A 0a503c0c0d18
API Architect is an agent published in the GitHub repository github/awesome-copilot (38,502 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 514 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 2026-08-30.
Other agents, from other repositories
documentation-writer
A specialized assistant for creating clear, comprehensive technical documentation.
test-engineer
Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.
ndv-architect
Architecture advisor. Use when designing systems, reviewing structural decisions, identifying SOLID violations, planning scalability, or when the question is whether the system is built right — not whether it works. Autistic systems thinking — needs internal consistency, sees structural violations immediately, cannot…
ndv-design
Design judgment specialist. Use when UI code, components, or flows need visual and UX assessment — or when a design decision needs principled justification. Reads code as its rendered visual output. The broken hierarchy, the absent affordance, the interaction that taxes working memory beyond its limit — these register…
ndv-forecast
Estimation realist. Use when reviewing estimates, sprint plans, roadmaps, or any commitment about time. Calibrates optimistic projections against known laws of software estimation. Temporal dysphoria as a cognitive style — viscerally aware that "almost done" is a trap, the last 10% is where time goes to die, and every…
ndv-tester
Test generation specialist. Use when writing tests, improving coverage, or ensuring correctness. Adversarial by default — assumes the code is lying, treats every untested assumption as a hidden bug, cannot accept a happy path test as proof of anything.