debug-teach

debug-teach is a skill for Claude Code, Codex from ashaychangwani/imprint. It costs 39 tokens per session (1,598 once invoked), scanned A, original, MIT.

A troubleshooting guide for Imprint teach runs, which generate tools from a website, including runs that fail, stall, or produce broken tools.

In plain words
What is it for?
Use it to investigate stuck, failed, or broken teach runs and inspect browser processes, compile logs, replay debugging, and traces.
Why use it?
It helps distinguish problems with environment settings, command options, browser replay, compilation, and diagnostic logs.

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/ashaychangwani/imprint/debug-teach
Any agent
npx skills add ashaychangwani/imprint --skill debug-teach
Clone the repo
git clone --depth 1 https://github.com/ashaychangwani/imprint

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 debug-teach

README.md
[![agentmods](https://agentmods.dev/badge/skills/ashaychangwani/imprint/debug-teach.svg)](https://agentmods.dev/skills/ashaychangwani/imprint/debug-teach)
Your own site
<a href="https://agentmods.dev/skills/ashaychangwani/imprint/debug-teach"><img src="https://agentmods.dev/badge/skills/ashaychangwani/imprint/debug-teach.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,598 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 $0.00039 $0.01598
Opus 5 $0.00019 $0.00799
Sonnet 5 $0.00008 $0.00320
Haiku 4.5 $0.00004 $0.00160

Measured 5d ago against content hash 18622c9b37f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug-teach 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/debug-teach/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debug an imprint teach run

Use this when a teach run failed, is stuck, was slow, or produced broken tools.

Step 1 — Determine what happened

Ask the user (or infer from context) which scenario applies:

Scenario Go to
Teach is currently running and looks stuck Step 2a
Teach finished but tools are broken Step 2b
Teach errored out Step 2c
Teach was slow and user wants to know why Use /imprint-teach-deepdive instead

Step 2a — Stuck teach (still running)

Check what stage it's in:

# See if the compile-log is being written (growing = still compiling)
ls -la ~/.imprint/<site>/*/.compile-log.json

# Check if Chrome is still alive (replay/record stage)
pgrep -fl chromium || pgrep -fl chrome

# If tracing was on, check the last span
bun run scripts/analyze-phoenix.ts --kind teach --last 1

Common stuck points:

  • Replay stage: browser hung waiting for a network response. Kill and re-run; check IMPRINT_REPLAY_DEBUG=1 output at /tmp/imprint-replay-debug-*.log
  • Compile agent looping: the agent is retrying a failing verification. Check the tail of .compile-log.json
  • Shared module build: a module failed to verify and is retrying. Look for pruning vs built + verified in stderr

Step 2b — Teach finished but tools are broken

# Run audit to get a structured report
bun run src/cli.ts audit <site> --json

# Read the audit report
cat ~/.imprint/<site>/.audit-report.json | jq '{score, verdicts: [.verdicts[] | {tool: .tool, verdict: .verdict}]}'

# Read the compile agent's full conversation for a broken tool
cat ~/.imprint/<site>/<broken-tool>/.compile-log.json | jq '.[].role' | head -20

# Check the tool plan the agent was given
cat ~/.imprint/<site>/<broken-tool>/.tool-plan.md

# Test the playbook interactively
bun run src/cli.ts playbook <site> --headed --trace --param key=value
# Screenshots land at /tmp/imprint-playbook-<tool>-step<N>-<ts>.png

Step 2c — Teach errored out

Read the full file on GitHub · 158 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 · 158 lines · 39 tokens per session scan A 18622c9b37f8

Subscribe to this mod's changes

debug-teach is a skill published in the GitHub repository ashaychangwani/imprint (21 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 1,598 once invoked, about $0.0002 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

writing-gauntlet-stories

Use when writing or reviewing a Gauntlet story card. Establishes the calibration framing — outcomes, persona binding, observable acceptance criteria — and explicitly rules out wrong-shaped frames (Agile user stories, QA step-scripts, BDD Given/When/Then) so prior knowledge does not contaminate the card.

prime-radiant-inc/gauntlet · 70 tokens

x402

Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…

browser-use/browser-use · 175 tokens

browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.

browser-use/browser-use · 26 tokens

cloud

Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation. Use this skill whenever the user needs help with the Cloud REST API (v2, v3, or v4), browser-use-sdk (Python or TypeScript), X-Browser-Use-API-Key authentication, cloud sessions, browser profiles, profile sync, CDP…

browser-use/browser-use · 177 tokens

open-source

Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…

browser-use/browser-use · 137 tokens

tool-prompt-optimization

Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…

can1357/oh-my-pi · 0 tokens