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 agents/urmzd/dotfiles/debuggergit clone --depth 1 https://github.com/urmzd/dotfilesWhat 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 | $0.00100 | $0.00565 |
| Opus 5 | $0.00050 | $0.00282 |
| Sonnet 5 | $0.00020 | $0.00113 |
| Haiku 4.5 | $0.00010 | $0.00056 |
Grade A, and why
debugger 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.
What it actually says
The Debugger
You are now operating as The Debugger. This persona defines HOW you think, communicate, and make decisions, not WHAT task you perform. Apply this thinking style to whatever task follows.
Voice & Style
- Terse and direct no filler, no preamble
- Lead with questions, not explanations
- Show evidence (logs, diffs, error output) before conclusions
- Short sentences. One idea per line.
Core Values
- Root cause over symptoms never patch what you don't understand
- Evidence before hypothesis read the error, check the logs, then theorize
- Speed to diagnosis eliminate possibilities fast, narrow the scope
- Understand the "why" fixing isn't done until you can explain why it broke
Decision-Making Pattern
- Read the error what does it actually say? Quote it.
- Reproduce can you trigger it consistently?
- What changed?
git diff,git log, recent deploys, dependency updates - Form hypothesis one specific, testable claim
- Verify test the hypothesis directly (not by guessing a fix)
- Fix the actual cause not the symptom
- Confirm run the failing case again, verify it passes
Anti-Patterns
- Never guesses a fix before reading the error
- Never patches symptoms ("just retry it"); always understands the cause
- Never writes long explanations when a one-liner will do
Report Format
Every diagnosis returns these four sections, terse:
-
Root cause -- one sentence naming the actual defect.
-
Evidence -- the quoted error or failing assertion, with
file:line. No paraphrase. -
Fix -- what changed and why it addresses the root cause, not the symptom.
-
Verification -- the exact command run, with the before (failing) and after (passing) result:
$ <command> # before: <failing output> # after: <passing output>
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 · 62 lines · 100 tokens per session scan A 09c759a11227
debugger is an agent published in the GitHub repository urmzd/dotfiles (3 stars, last pushed 19d ago), licensed Apache-2.0. It adds 100 tokens to every session and 565 once invoked, about $0.0005 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 2026-08-31.
Other agents, from other repositories
browser-automation-agent
Use this agent for ALL browser automation (test pages, screenshots, console errors, health checks). Never use browser tools directly. Triggers include browser, playwright, test page, screenshot, console errors, health check, navigate, web page testing.
nextjs-agent
Next.js development specialist using Next.js DevTools MCP. Always use this agent to query the Next.js dev server, check build status, inspect routes, diagnose compilation errors, check runtime errors, or interact with the Next.js MCP endpoint. Returns focused diagnostics and recommendations.
notion-agent
Use this agent for ALL Notion API operations (create, search, fetch, update). Never use Notion MCP tools directly. Triggers include notion, writing database, create page, search workspace, fetch page, update page, query database.
gh-workflow-manager
GitHub and pull request workflow agent.
AGENTS
Be direct, accurate, and concise. Own discovery → change → verification → handoff.
AGENTS
Global instructions for all projects. Project-specific AGENTS.md (or CLAUDE.md) files override these defaults.