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 setup-agent-replaygit 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/setup-agent-replay)<a href="https://agentmods.dev/skills/raindrop-ai/workshop/setup-agent-replay"><img src="https://agentmods.dev/badge/skills/raindrop-ai/workshop/setup-agent-replay/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/setup-agent-replay"><img src="https://agentmods.dev/badge/skills/raindrop-ai/workshop/setup-agent-replay.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 281 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00074 | $0.02640 |
| Opus 5.5 | $0.00030 | $0.01056 |
| Sonnet 5.5 | $0.00015 | $0.00528 |
| Haiku 4.5 | $0.00007 | $0.00264 |
Grade A, and why
setup-agent-replay 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.
curl -fsS http://127.0.0.1:<port>/health Copies of this mod
1 near-identical copy found in the catalogue:
- setup-agent-replay — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running in the user's agent repository, not in Workshop.
Your job is to make the agent replayable from Raindrop Workshop without the user manually starting a replay server.
Target Contract
Workshop expects:
.raindrop/agents.yamlcommitted in the agent repo.- A replay server command in that yaml, plus
cwdwhen the command must run from a subdirectory. - A replay server with:
GET /healthPOST /replay
- A local project registration via
raindrop replay register.
Replay server ports must be in 61020-61044.
Workshop runs on http://localhost:5899.
If Raindrop MCP is not available or cannot reach Workshop, run:
raindrop workshop
Then retry the MCP/tool call. Do not stop just because the MCP server is unavailable.
If .raindrop/agents.yaml Already Exists
Before changing anything, read .raindrop/agents.yaml.
Ask the user whether to:
- Start/register the existing replay setup.
- Add a new agent replay entry.
If they choose start/register:
- Run the configured command if needed.
- Verify
GET /health. - Run
raindrop replay register. - Stop. Do not scaffold a duplicate server.
Setup Steps
1. Identify The Agent
Find:
- Event name used by tracing (
eventMetadata({ eventName: ... }), equivalent SDK call, or current Workshop run). - Agent entry point to invoke.
- Runtime context the agent requires, such as
orgId,orgPublicId,convoId,userId,source. - Model defaults and obvious supported model overrides.
- Existing script/package manager conventions.
If the agent is not instrumented with Raindrop/Workshop tracing, stop and tell the user to instrument it first.
2. Infer Input And Prefill
Create:
input:
orgPublicId: string
orgId: number
prefillFromTrace:
orgPublicId: properties.orgPublicId
orgId: properties.orgId
input is the shape passed to the replay server as request.context.
prefillFromTrace tells Workshop how to prefill that context from the selected trace. The user may edit the values in the UI before replay.
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 · 356 lines · 74 tokens per session scan A 7a6bb19697aa
setup-agent-replay is a skill published in the GitHub repository raindrop-ai/workshop (1,115 stars, last pushed 3d ago), licensed MIT. It adds 74 tokens to every session and 2,640 once invoked, about $0.0003 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
tdd-workflow
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
e2e-testing
Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies. Use when writing Playwright tests, structuring page objects, or fixing flaky E2E runs in CI.
dogfood
Exploratory QA of web apps: find bugs, evidence, reports.
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.