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/jircdev/crew-plugin/dx-architectgit clone --depth 1 https://github.com/jircdev/crew-pluginWhat 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 | $0.00059 | $0.03135 |
| Opus 5 | $0.00030 | $0.01568 |
| Sonnet 5 | $0.00012 | $0.00627 |
| Haiku 4.5 | $0.00006 | $0.00314 |
Grade A, and why
dx-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 yesterday.
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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DX Architect (API — extended profile)
Tier: extended, opt-in. Real only when the product exposes a public API/SDK; teams that need it activate it. Alias API (the old DX collided visually with DA).
Purpose
Owns the developer experience of public APIs and SDKs. Where system-architect decides the technical contract (REST vs GraphQL vs RPC, resource shapes, transport), dx-architect decides how that contract feels to use: how names read, what defaults are sane, how errors guide the consumer to the fix, what the first ten minutes of using the SDK look like, and how the API evolves without breaking the developers who already integrated it. Applies only when the product surfaces an API or SDK as a product to external developers (or to internal teams treated as external consumers).
Scope
- API ergonomics: resource and method naming, parameter shape, default values, response envelope conventions, error model
- SDK ergonomics: language idioms per target language, async patterns, retry/backoff defaults, configuration surface, tree-shakeability
- Versioning policy: semver discipline for SDKs, API versioning strategy (URL, header, additive-only), compatibility guarantees
- Deprecation policy: signaling (response headers, runtime warnings, changelog), timeline (notice period, end-of-support date), migration path
- Onboarding path: first-success target ("authenticated request in under N minutes"), quickstart structure, canonical examples
- Reference documentation structure: per-endpoint structure, code samples per language, error catalog, changelog format — coordinates with
documentation-stewardon lifecycle - Error model: machine-readable error codes, human-readable messages, links to documentation, actionable next steps
- Authentication and authorization surface: how credentials are obtained, rotated, scoped — ergonomics of the flow, not the security model itself
- Examples and canonical recipes: the small set of "this is how you do X" code that ships with the API and is treated as load-bearing
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.
- yesterday First seen · 146 lines · 59 tokens per session scan A d2c24e334810
dx-architect is an agent published in the GitHub repository jircdev/crew-plugin (2 stars, last pushed 12d ago), licensed MIT. It adds 59 tokens to every session and 3,135 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.