instrument-agent

A command that adds Progress Observability tracking to an existing Python, TypeScript, or .NET AI agent. The tracking records runs so they can be reviewed later.

In plain words
What is it for?
Use it to detect the project setup, add the matching tracking package and configuration, verify the agent can run, and learn where to confirm that traces are arriving.
Why use it?
It removes the need to add monitoring manually and keeps the code changes small.

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/instrument-agent
Clone the repo
git clone --depth 1 https://github.com/observability-oss/progress-observability-plugin
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 250 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 $0.00029 $0.00250
Opus 5 $0.00015 $0.00125
Sonnet 5 $0.00006 $0.00050
Haiku 4.5 $0.00003 $0.00025

Measured 2d ago against content hash d0724b552f60, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

instrument-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/instrument-agent.md · 22 lines

What it actually says

Use the instrument-agent skill.

Target: $ARGUMENTS

Detect the language, LLM SDKs/frameworks, any existing telemetry, and the config style — and report the planned diff before editing. Then wire instrumentation per the matching language reference (references/python.md, typescript.md, or dotnet.md) with the smallest possible diff: latest package, init at process start before any LLM client exists, Integration key (ac_p_…) via config, agreed app_name, flush on exit. Have the app run once (the decorator/manual-span path works with no LLM credentials). This skill does not read the platform back — tell the user wiring is done, then have them run their agent and confirm the traces are flowing in at observability.progress.com for their app_name.

If no target was given and the working directory isn't obviously the agent to instrument, ask which project to instrument before touching anything.

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 · 22 lines · 29 tokens per session scan A d0724b552f60

Subscribe to this mod's changes

instrument-agent is a command published in the GitHub repository observability-oss/progress-observability-plugin (2 stars, last pushed 7d ago), licensed MIT. It adds 29 tokens to every session and 250 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.