adk-debug

A debugging guide for ADK (Agent Development Kit) agents that examines sessions, events, tool calls, and the exact request sent to the language model.

In plain words
What is it for?
Use it to reproduce failures with the ADK command line, inspect event logs and traces, investigate ignored tools or tool errors, and diagnose hangs.
Why use it?
It helps identify whether a problem comes from routing, a tool, the model request, or the agent’s runtime behavior.

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/google/adk-python/adk-debug
Any agent
npx skills add google/adk-python --skill adk-debug
Clone the repo
git clone --depth 1 https://github.com/google/adk-python

Made for: Claude Code, Codex.

Per session 191 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 875 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 $0.00191 $0.00875
Opus 5 $0.00096 $0.00438
Sonnet 5 $0.00038 $0.00175
Haiku 4.5 $0.00019 $0.00088

Measured yesterday against content hash 141e9442ee9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adk-debug 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 yesterday.

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/adk-debug/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugging ADK agents

Two entry points. Default to adk run: one process, no server, and --jsonl output that pipes straight into grep or python3. Switch to adk web when you need the browser UI, a persisted session you can click through, or the trace endpoints that expose the exact LLM request.

First moves

  1. Reproduce headlessly: adk run --jsonl {agent_dir} "{query}". Without --jsonl, adk run prints only text parts — tool calls and tool errors are invisible.
  2. Read the log file. adk run writes to /tmp/agents_log/agent.latest.log and nothing to the terminal; adk web does the opposite. See logs-and-traces.md.
  3. Match the symptom in failure-modes.md before reading source — most reports are one of a handful of known shapes.
  4. If the text is fine but the routing is not, dump the events and read author, branch, nodeInfo.path, and actionsevent-flow.md.
  5. If the model itself misbehaved, read what it actually received from the call_llm span rather than guessing from the agent definition — logs-and-traces.md.

References

  • cli-run.mdadk run flags, the JSONL event shape, multi-turn and human-in-the-loop resume, exit codes, driving a Runner from Python.
  • web-api.md — starting adk web, listing and reading sessions over HTTP, posting test messages to /run_sse.
  • logs-and-traces.md — log levels and where each command writes them, the trace endpoints, span attributes, and the env vars that control whether prompts appear in spans.
  • failure-modes.md — ADK-specific symptoms with the cause and a concrete check for each.
  • event-flow.md — how an invocation becomes events, callback order, the event fields that matter, and where each stage lives in the source.

Read the full file on GitHub · 67 lines

Files

What ships with it

5 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. yesterday First seen · 67 lines · 191 tokens per session scan A 141e9442ee9f

Subscribe to this mod's changes

adk-debug is a skill published in the GitHub repository google/adk-python (21,331 stars, last pushed 2d ago), licensed Apache-2.0. It adds 191 tokens to every session and 875 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.