debugging-local-task-agent-runs

debugging-local-task-agent-runs is a skill for Claude Code, Codex from PostHog/posthog-foss. It costs 201 tokens per session (1,991 once invoked), scanned A, original, MIT.

A troubleshooting guide for local PostHog task runs, where a setup wizard and coding agent run inside a Docker container through a Temporal workflow. Docker packages the run in an isolated container, while Temporal coordinates its steps.

In plain words
What is it for?
Use it to inspect the wizard and agent logs, check local configuration, and investigate why a local task run failed or stopped responding.
Why use it?
The workflow screen hides much of the useful output, so failures, hangs, and silent runs are difficult to diagnose from the timeline alone.

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/posthog/posthog-foss/debugging-local-task-agent-runs
Any agent
npx skills add PostHog/posthog-foss --skill debugging-local-task-agent-runs
Clone the repo
git clone --depth 1 https://github.com/PostHog/posthog-foss

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for debugging-local-task-agent-runs

README.md
[![agentmods](https://agentmods.dev/badge/skills/posthog/posthog-foss/debugging-local-task-agent-runs.svg)](https://agentmods.dev/skills/posthog/posthog-foss/debugging-local-task-agent-runs)
Your own site
<a href="https://agentmods.dev/skills/posthog/posthog-foss/debugging-local-task-agent-runs"><img src="https://agentmods.dev/badge/skills/posthog/posthog-foss/debugging-local-task-agent-runs.svg" alt="Measured on agentmods" height="20"></a>
Per session 201 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,991 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 5.1 $0.00201 $0.01991
Opus 5 $0.00101 $0.00996
Sonnet 5 $0.00040 $0.00398
Haiku 4.5 $0.00020 $0.00199

Measured 5d ago against content hash 36f3b0aca9f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

debugging-local-task-agent-runs 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 5d 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.

.agents/skills/debugging-local-task-agent-runs/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugging local task/agent runs

A "cloud run" of the Tasks product (e.g. the setup-wizard cloud_run endpoint) executes as the Temporal process-task workflow on the development-task-queue. Locally (SANDBOX_PROVIDER=docker) each run gets a Docker sandbox container in which two things happen in sequence:

  1. run_wizard activity — runs the published @posthog/wizard to integrate PostHog (writes /tmp/posthog-wizard.log).
  2. agent-server — the coding agent that commits the wizard's changes, opens the PR, and keeps it green (writes /tmp/agent-server.log).

The hard part of debugging is that the Temporal UI doesn't show this output — workflow result/failure payloads are binary/encrypted, and the activity captures the wizard/agent output to the run's logs, not to the timeline. This skill is how you actually read it.

Prerequisites: env for local cloud runs

Cloud runs only work locally if all of these are set in .env.local (values shown are the local targets — never commit real secrets). Inside the Docker sandbox, localhost is the container itself, so PostHog URLs use host.docker.internal.

Key Purpose / local value
SANDBOX_PROVIDER "docker" — route sandboxes to local Docker instead of Modal
SANDBOX_MCP_URL "http://host.docker.internal:8787/mcp" — MCP server the agent uses
SANDBOX_LLM_GATEWAY_URL "http://host.docker.internal:3308" — local LLM gateway the agent routes model calls through
SANDBOX_JWT_PRIVATE_KEY signs the scoped sandbox tokens
GITHUB_APP_CLIENT_ID your local GitHub App (clone + PR)
GITHUB_APP_CLIENT_SECRET ""
GITHUB_APP_SLUG ""
GITHUB_APP_PRIVATE_KEY ""
LLM_GATEWAY_ANTHROPIC_API_KEY real Anthropic key the local gateway proxies to (read via the gateway's LLM_GATEWAY_ env prefix)

Read the full file on GitHub · 115 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. 5d ago First seen · 115 lines · 201 tokens per session scan A 36f3b0aca9f3

Subscribe to this mod's changes

debugging-local-task-agent-runs is a skill published in the GitHub repository PostHog/posthog-foss (712 stars, last pushed today), licensed MIT. It adds 201 tokens to every session and 1,991 once invoked, about $0.0010 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 2026-08-30.

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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens