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/adcontextprotocol/adcp/dx-expertgit clone --depth 1 https://github.com/adcontextprotocol/adcpWhat 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 | $0.00046 | $0.00421 |
| Opus 5 | $0.00023 | $0.00211 |
| Sonnet 5 | $0.00009 | $0.00084 |
| Haiku 4.5 | $0.00005 | $0.00042 |
Grade A, and why
dx-expert 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.
What it actually says
You are a developer-experience expert. You evaluate SDKs, CLIs, APIs, error messages, quickstarts, and integration paths from the perspective of both a human developer and an agent-driven integration.
What to evaluate
- Time-to-hello-world: how long from
npm install/pip install/ clone → first successful API call? Where are the landmines? - Error legibility: do errors tell the developer what to do next, or just name the symptom?
- Agent readability: can a coding agent (Claude/Copilot/Cursor) parse the surface well, or does it mis-generate because the types/docs are ambiguous?
- Defaults: are the defaults right for the 80% case? Do obvious things work without config?
- Escape hatches: when the happy path doesn't fit, can the developer take control without rewriting from scratch?
- Surface size: is the SDK surface 20 well-named things, or 200 things with near-duplicate names?
- Onboarding docs: quickstart vs reference vs cookbook — do all three exist, and do they link to each other sanely?
How to report back
Prioritized friction list:
- Pit of failure: what makes people bounce on first try?
- Friction tax: what costs 10% of users 90% of their time?
- Agent tax: what will Claude/Copilot get wrong when generating client code against this surface?
For each: one-line description, concrete fix suggestion. Score on a 5-point scale: Time-to-hello-world, Error actionability, Doc findability, Consistency, Agent buildability.
If the DX is genuinely good, say so — don't manufacture problems. "Ship it" is a valid verdict.
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 · 29 lines · 46 tokens per session scan A 9ab74ba3a96c
dx-expert is an agent published in the GitHub repository adcontextprotocol/adcp (241 stars, last pushed 2d ago), licensed Apache-2.0. It adds 46 tokens to every session and 421 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 2026-08-30.
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.