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/neotoma/debugnpx skills add markmhendrickson/neotoma --skill debuggit clone --depth 1 https://github.com/markmhendrickson/neotomaWhat 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 | $0.00004 | $0.06801 |
| Opus 5 | $0.00002 | $0.03401 |
| Sonnet 5 | $0.00001 | $0.01360 |
| Haiku 4.5 | $0.00000 | $0.00680 |
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 2d 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.
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 }) How it starts
The opening of the file, as written. The whole thing — 988 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: debug description: Debug workflow per foundation command. triggers:
- debug
- /debug
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.
- 2d ago First seen · 988 lines · 4 tokens per session scan A ebf02ea699ec
debug is a skill published in the GitHub repository markmhendrickson/neotoma (29 stars, last pushed 5d ago), licensed MIT. It adds 4 tokens to every session and 6,801 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
clean-user-facing-text
Clean and finalize authorized natural-language text intended for readers by auditing suspicious invisible Unicode and rewriting prose while preserving facts, meaning, and the writer's voice. Use when the user asks to clean, humanize, polish, or finalize articles, manuscripts, reports, documentation, emails, product…
openbiliclaw-adapter
Use OpenBiliClaw's versioned Agent Bridge CLI to read multi-source recommendations, profile state, dialogue, probes, saved lists, and submit explicit feedback.
writing-specs
Use when authoring a spec or implementation plan, or planning multi-task work.
release
Use when releasing a version, bumping project versions, or pushing release tags.
add-platform-source
Use when adding, integrating, repairing, hardening, completing, auditing, testing, or releasing an OpenBiliClaw platform/source adapter, including anonymous or credentialed APIs, browser-extension tasks and identity, source auth/status, bootstrap and incremental sync, formal discover, configuration, recommendation…
bilibili_browse
Browse Bilibili pages using agent-browser for visual exploration and DOM interaction.