raindrop-ai/workshop is a local debugging tool that records an AI coding agent’s tokens, tool calls, and other execution spans as live traces. Developers use it to inspect agent behavior, create evaluations against their codebases, replay production traces, and iterate until tests pass. Its catalogue skills and instruction connect coding agents to Workshop’s tracing and evaluation workflows.
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 skills add raindrop-ai/workshop --skill instrument-agentgit clone --depth 1 https://github.com/raindrop-ai/workshopWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/raindrop-ai/workshop/instrument-agent)<a href="https://agentmods.dev/skills/raindrop-ai/workshop/instrument-agent"><img src="https://agentmods.dev/badge/skills/raindrop-ai/workshop/instrument-agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/raindrop-ai/workshop/instrument-agent"><img src="https://agentmods.dev/badge/skills/raindrop-ai/workshop/instrument-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00114 | $0.03167 |
| Opus 5.5 | $0.00046 | $0.01267 |
| Sonnet 5.5 | $0.00023 | $0.00633 |
| Haiku 4.5 | $0.00011 | $0.00317 |
Grade A, and why
instrument-agent scanned grade A 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Check whether Workshop is running: `curl -fsS http://localhost:5899/health`. Copies of this mod
1 near-identical copy found in the catalogue:
- instrument-agent — 95% identical, 9 lines differ
How it starts
The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are helping instrument an AI agent so its next meaningful run appears in Raindrop Workshop. Workshop is the local viewer; it does not run the agent. The user's agent app runs the workflow, the Raindrop SDK captures model/tool boundaries and context, and Workshop renders that telemetry as a debuggable run.
Use supported Raindrop SDK/integration paths. Do not hand-wire Workshop ingestion endpoints or invent SDK APIs. If the repo's telemetry setup is too custom to instrument safely, stop with a clear handoff to the Raindrop docs or team.
Use Docs First
Raindrop SDK and integration APIs move quickly. Before writing code, fetch docs in parallel: the docs index, the likely stack-specific page, and installed package README/types when available.
- Docs index:
https://raindrop.ai/docs/llms.txt - Introduction:
https://raindrop.ai/docs/introduction - Integration overview:
https://raindrop.ai/docs/integrations/overview - Core SDKs:
https://raindrop.ai/docs/sdk/typescript,/sdk/python,/sdk/rust,/sdk/go,/sdk/http-api,/sdk/browser - Framework integrations:
https://raindrop.ai/docs/integrations/<name>such asvercel-ai-sdk,claude-agent-sdk,langchain,openai-agents,pydantic-ai,google-adk,bedrock,azure-openai,vertex-ai
Use this skill for the workflow and Workshop-specific judgment. Use the docs and installed package README/types for exact install commands, imports, options, and signatures.
Core Rules
- Give visible progress. Say what phase you are in, what you learned, and what you are about to edit. Do not silently research for minutes.
- Report often but briefly: one or two sentences per update, focused on current phase, finding, and next step. Avoid long dumps unless you are blocked and need a decision.
- Before editing any file, tell the user about the intended change, and give them an honest assessment for how risky it might be.
- Instrument one real agent entry point first. If several are plausible, ask which one should appear in Workshop.
- First get a minimal useful run into Workshop, then enrich it. Do not trace every helper/tool/sub-agent before Phase 1 works.
- Respect existing telemetry ownership. If the repo already initializes OpenTelemetry, Sentry, Datadog, Honeycomb, Traceloop, LangSmith, or another provider, do not create a competing provider.
- Updating the matching Raindrop SDK/integration to the latest available version is mandatory before instrumentation edits. Do not proceed on an older installed SDK just because it is already present.
- Prefer installed package docs/types over memory. If an API is not present in the installed package, do not use it.
- Verification is required. Success means Workshop shows a useful run, not just that dependencies installed.
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.
- 1mo ago First seen · 263 lines · 114 tokens per session scan A af8d673a2a40
instrument-agent is a skill published in the GitHub repository raindrop-ai/workshop (1,115 stars, last pushed yesterday), licensed MIT. It adds 114 tokens to every session and 3,167 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
trulens-instrumentation
Instrument LLM apps with TruLens OTEL-based tracing - from setup to debugging and optimization.
tracelet-instrument
Instrument an AI agent or LLM app with OpenTelemetry and watch its runs live in tracelet (local DevTools). Use when asked to add tracing/observability to an agent, or to debug what an agent actually did.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
triage-issues
Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…
agent-merge-conflict-arbiter
Neutral arbiter for merge conflicts between two agents.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.