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 agentmods add skills/markmhendrickson/foundation/debugnpx skills add markmhendrickson/foundation --skill debuggit clone --depth 1 https://github.com/markmhendrickson/foundationWhat 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 | $0.00008 | $0.06776 |
| Opus 5 | $0.00004 | $0.03388 |
| Sonnet 5 | $0.00002 | $0.01355 |
| Haiku 4.5 | $0.00001 | $0.00678 |
Grade A, and why
debug 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
remoteUrl = execSync('git remote get-url origin', { cwd: repoPath }) This is a copy
100% identical to debug — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 981 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Command
Purpose
Check for pending error reports and debug/resolve them. Supports cross-repo error queue checking for sibling repositories. Also manages the error debugging automation watcher.
Command Usage
/debug [action|target-repo-name]
Modes of Operation:
The command operates in two modes based on the first argument:
1. Watcher Management Mode
If the first argument is a watcher management action (start, stop, status, logs, restart), manage the error debugging automation watcher:
/debug start # Start the error debugging watcher
/debug stop # Stop the running watcher
/debug status # Check watcher status
/debug logs # Show watcher logs
/debug restart # Restart the watcher
2. Error Debugging Mode (Default)
If the first argument is not a watcher action (or no arguments provided), check and debug pending errors:
/debug # Check current repo's pending errors (default)
/debug neotoma # Check sibling repo's pending errors
/debug personal-project # Check another sibling repo
Note: To check watcher status, use /debug status. The default behavior (no arguments) checks for pending errors in the current repository.
Parameters:
action(optional): Watcher management action (start,stop,status,logs,restart)- If provided, manages the error debugging automation watcher
- If omitted: Defaults to error debugging mode (check pending errors)
target-repo-name(optional): Name of sibling repository to check for pending errors- Must be a sibling repository (shares same parent directory)
- Only used if first argument is not a watcher action
Examples:
# Watcher management
/debug start # Start watcher
/debug status # Check watcher status
/debug logs # View watcher logs
/debug stop # Stop watcher
# Error debugging
/debug # Check current repo's pending errors
/debug neotoma # Check sibling repo's pending errors
/debug --list-only # List errors without debugging
/debug --all --auto # Process all errors automatically
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.
- yesterday First seen · 981 lines · 8 tokens per session scan A 532197230375
debug is a skill published in the GitHub repository markmhendrickson/foundation (2 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 6,776 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). It is 100% identical to debug, differing in 7 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…