image-debug

A troubleshooting guide for failed projtool image builds. An image build creates a reusable project environment by running setup.sh inside a temporary builder machine.

In plain words
What is it for?
Use it when setup.sh exits with an error during an image build. It helps inspect the error, test a fix remotely, and update setup.sh when the fix should be kept.
Why use it?
Build failures can leave useful files and error details in the still-running builder. The guide helps identify the failure from the logs and choose a fix without losing that debugging state.

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/zhyx12/projtool/image-debug
Any agent
npx skills add zhyx12/projtool --skill image-debug
Clone the repo
git clone --depth 1 https://github.com/zhyx12/projtool

Made for: Claude Code, Codex.

Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,412 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00122 $0.01412
Opus 5 $0.00061 $0.00706
Sonnet 5 $0.00024 $0.00282
Haiku 4.5 $0.00012 $0.00141

Measured yesterday against content hash 6727c921dbc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

image-debug scanned grade C with 2 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf /tmp/* # if anything is staged there

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSI https://mirrors.aliyun.com/ -o /dev/null && echo OK || echo BAD
src/projtool/assets/project_skills/image-debug/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

image-debug

projtool builds project images by spinning up a one-shot AutoDL "builder" instance, running the project's setup.sh inside it, and (on success) saving the result as a custom image. This skill activates when something goes wrong during setup.sh. Most failures fall into a small number of categories, listed below — read the relevant references/ file before proposing a fix.

Workflow

  1. Don't tear down on first failure. The builder instance is alive and has all the partial state. Closing it loses minutes of debug context.
  2. Read the tail of stderr. mcp__projtool__remote_exec returns stderr_tail (and stdout_tail) inline in the response; the full output is written to the file at log_path in the result. The error message is almost always in the last 30 lines of stderr_tail.
  3. Match the error to a category (below). Read the matching reference.
  4. Propose a fix. Either patch setup.sh locally + push it to the instance via write_remote_file, or run the fix command directly via remote_exec to validate before bake-in. For non-trivial changes, patching setup.sh is preferred — it makes the next build idempotent. For AutoDL PyTorch base images, make the first line after set -euo pipefail export Miniconda onto PATH: export PATH="/root/miniconda3/bin:$PATH". Some non-interactive SSH shells do not source bashrc, so plain python / python3 may otherwise be missing even though the image has conda.
  5. Re-run the failed step, not the whole setup.sh. Most steps are idempotent (apt-get, pip install). Only re-run the full script when confident the earlier steps will no-op cleanly.
  6. On success, confirm the build passes end-to-end before saving. Then: image_save (non-blocking — returns pending_image_uuid immediately) → poll image_save_status until image_status='ready'image_build_finalize. Saving an image with hidden partial state (e.g., wrong CUDA toolkit) creates a long-tail bug.
  7. On give-up, image_build_abandon releases the builder. Don't leave builders running — they bill at GPU rates.

Read the full file on GitHub · 109 lines

Files

What ships with it

3 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 · 109 lines · 122 tokens per session scan C 6727c921dbc2

Subscribe to this mod's changes

image-debug is a skill published in the GitHub repository zhyx12/projtool (1 stars, last pushed 18d ago), licensed MIT. It adds 122 tokens to every session and 1,412 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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

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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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