scaffold-agent

A tool for starting a new .NET AI-agent project with observability already connected. Observability means collecting information about how the agent runs.

In plain words
What is it for?
Creating an instrumented .NET agent from a starter template, then defining its instructions, tools, name, and knowledge sources.
Why use it?
It supplies the project setup and monitoring connection so you can focus on the agent's purpose, actions, and reference documents.

Skill for Claude CodeCodex

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 skills/observability-oss/progress-observability-plugin/scaffold-agent
Any agent
npx skills add observability-oss/progress-observability-plugin --skill scaffold-agent
Clone the repo
git clone --depth 1 https://github.com/observability-oss/progress-observability-plugin

Made for: Claude Code, Codex.

Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,467 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00085 $0.01467
Opus 5 $0.00043 $0.00733
Sonnet 5 $0.00017 $0.00293
Haiku 4.5 $0.00009 $0.00147

Measured 2d ago against content hash f97ea904bd42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

scaffold-agent scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf <target-folder>/.git
skills/scaffold-agent/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scaffold an instrumented .NET agent

Create a working, already-instrumented .NET agent for the user's domain by starting from the observability-oss/dotnet-agent-starter template and filling in only its marked slots.

This skill writes files. Most of this plugin only reads the Progress Observability Platform; this skill creates a project on disk and makes no MCP calls at all. (Its sibling instrument-agent retrofits observability onto a project that already exists.)

The template already contains the observability wiring, the pinned package versions, and the configuration layering — all of it verified to build. Your job is the domain layer: the agent's name, its instructions, its tools, and its knowledge corpus. Everything else is copied through untouched.

Workflow

  1. Gather what you need. Ask for whatever the user hasn't already said:

    • What the agent does — one or two sentences. This becomes its instructions.
    • Its actions — 2–4 things it should be able to do (look something up, create a record, run a calculation). These become tools.
    • Grounding documents — does it answer from a body of knowledge? If so, what kind of documents.
    • A short name — used for the project, the app name, and the folder. Slugify it (lowercase, hyphens) for the app name.

    Don't over-interview. Two exchanges is plenty; sensible defaults beat a questionnaire.

  2. Fetch the template. Prefer the newest release tag; fall back to the default branch when the repo has no tags yet:

    REPO=https://github.com/observability-oss/dotnet-agent-starter.git
    TAG=$(git ls-remote --tags --refs --sort=-v:refname "$REPO" 'v*' | head -n1 | sed 's|.*refs/tags/||')
    git clone --depth 1 ${TAG:+--branch "$TAG"} "$REPO" <target-folder>
    rm -rf <target-folder>/.git
    

    Scaffold into a new folder named after the agent, never into a folder that already has files in it. If the clone fails (no network, no git), stop and give the user the clone command to run themselves — do not reconstruct the template from memory. Getting the observability wiring or the package versions subtly wrong is worse than not scaffolding.

Read the full file on GitHub · 108 lines

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 · 108 lines · 85 tokens per session scan C f97ea904bd42

Subscribe to this mod's changes

scaffold-agent is a skill published in the GitHub repository observability-oss/progress-observability-plugin (2 stars, last pushed 7d ago), licensed MIT. It adds 85 tokens to every session and 1,467 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens