scaffold-agent

A command that creates a new .NET AI agent from a starter project with Progress Observability already connected. Progress Observability records information about how the agent runs.

In plain words
What is it for?
Use it to start a .NET agent with a name, instructions, tools, and data source, then build and run it with health-check guidance.
Why use it?
It avoids setting up the project structure and monitoring connection by hand while keeping the starter’s existing configuration intact.

Command

Install

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.

agentmods
npx agentmods add commands/observability-oss/progress-observability-plugin/scaffold-agent
Clone the repo
git clone --depth 1 https://github.com/observability-oss/progress-observability-plugin
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 246 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.00246
Opus 5 $0.00013 $0.00123
Sonnet 5 $0.00005 $0.00049
Haiku 4.5 $0.00003 $0.00025

Measured 2d ago against content hash 86be61afdbc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scaffold-agent 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.

commands/scaffold-agent.md · 13 lines

What it actually says

Use the scaffold-agent skill.

Agent to build: $ARGUMENTS

Clone observability-oss/dotnet-agent-starter at its newest release tag (fall back to the default branch if it has no tags), drop the .git folder, and scaffold into a new folder named after the agent. Fill only the scaffold:-marked slots — app name, system prompt, tools, corpus — and leave the observability wiring, pinned package versions, and configuration layering exactly as they are. Tools get [Description] attributes and working stubs over plausible in-memory data, including at least one honest not-found path. Run dotnet build and make it pass before reporting success, then hand off with the dotnet user-secrets commands, dotnet run, and /health-check.

If the goal wasn't given, ask what the agent should do and which 2–4 actions it needs before cloning.

Changes

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.

  1. 2d ago First seen · 13 lines · 25 tokens per session scan A 86be61afdbc5

Subscribe to this mod's changes

scaffold-agent is a command published in the GitHub repository observability-oss/progress-observability-plugin (2 stars, last pushed 7d ago), licensed MIT. It adds 25 tokens to every session and 246 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 2026-08-31.