instrument-agent

A workflow for adding Progress Observability tracking to an existing AI agent or language-model application.

In plain words
What is it for?
Detecting the project's language and AI framework, adding the supported instrumentation, running the application once, and handing off instructions for checking traces.
Why use it?
It adds tracing with a small code change so the application's agent activity can later be inspected.

Skill for Claude CodeCodex

Part of the progress-observability plugin — 6 skills, 8 commands, 1 MCP server shipped together

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

Made for: Claude Code, Codex.

Or install progress-observability, the plugin that ships this one along with the rest of its 6 skills, 8 commands, 1 MCP server.

Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,264 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 $0.00139 $0.03264
Opus 5 $0.00069 $0.01632
Sonnet 5 $0.00028 $0.00653
Haiku 4.5 $0.00014 $0.00326

Measured 2d ago against content hash f00afd8244a8, 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.

skills/instrument-agent/SKILL.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instrument an existing agent

Retrofit Progress Observability onto an existing codebase with the smallest possible diff, then run it once so spans start flowing. For a project that does not exist yet, this is the wrong skill — it only edits what is already there.

This skill writes code — the instrumentation edits and nothing else. It never restructures the app, and it never reads the platform back: confirming the traces arrived is left to /health-check.

1 · Detect — before touching anything

Scan the repo and report what you found, then the diff you intend to make, before editing:

  • Language & entry pointpyproject.toml/requirements.txt, package.json (check "type": "module" — it decides the wiring path), *.csproj.

  • LLM SDKs and frameworks in use — imports of openai, anthropic, langchain, llama_index, @langchain/*, Microsoft.Extensions.AI, etc. Check each against the supported-instruments list in the language reference. A client pointed at an OpenAI-compatible endpoint (OpenRouter, LiteLLM, vLLM, Together, most gateways) counts as OpenAI — see the reference. A .NET agent built from AIProjectClient (Azure AI Foundry) has no wrappable chat client — different wiring; see the Foundry section in references/dotnet.md.

  • Existing telemetry — OpenTelemetry setup, Traceloop, or a previous Progress Observability init. Look for it before writing anything, and check the reference for ordering rather than assuming init belongs first.

    Python (measured). The SDK attaches to a provider the app already installed, so Progress ends up alongside the app's exporter rather than replacing it — but only if init runs after the app's own setup. Init first and the app's set_tracer_provider() becomes a no-op with one warning line, killing its existing telemetry while Progress spans keep arriving. Grep for set_tracer_provider / TracerProvider(. Details in references/python.md.

Read the full file on GitHub · 223 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 223 lines · 139 tokens per session scan A f00afd8244a8

Subscribe to this mod's changes

instrument-agent is a skill published in the GitHub repository observability-oss/progress-observability-plugin (2 stars, last pushed 7d ago), licensed MIT. It adds 139 tokens to every session and 3,264 once invoked, about $0.0007 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.

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