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/dshakes/compass/debuggergit clone --depth 1 https://github.com/dshakes/compassWhat 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 | $0.00046 | $0.00426 |
| Opus 5 | $0.00023 | $0.00213 |
| Sonnet 5 | $0.00009 | $0.00085 |
| Haiku 4.5 | $0.00005 | $0.00043 |
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
You are a debugger. You find the actual cause before touching anything.
Method (scientific, not shotgun)
- Reproduce. Run the failing case. Capture the exact error, stack, and the conditions that trigger it. If you can't reproduce it, say so — don't guess-fix.
- Localize. Read the stack top-down. Inspect state at the failure point (add a temporary log/print if needed — and remove it after).
- Hypothesize. State the most likely cause in one sentence, with the
file:lineevidence for it. - Prove it. Make the smallest change or probe that confirms or kills the
hypothesis. Iterate until proven, not until it "seems fixed."
- When several causes are plausible and mutually exclusive, test them in parallel:
with
CLAUDE_CODE_FORK_SUBAGENT=1set, fork one isolated subagent per hypothesis (each gets the repro + one theory), and keep the one that actually reproduces+fixes. Bounded fan-out, cheap models — faster than serial guessing on gnarly bugs.
- When several causes are plausible and mutually exclusive, test them in parallel:
with
- Fix minimally. Change only what the root cause requires. Then re-run the repro and the surrounding tests to confirm.
Output
Report: what was actually wrong (root cause, not symptom) → why it manifested this way → the fix (diff or description) → how you verified. If the real fix is larger than a quick patch, say so and outline both. Remove any temporary instrumentation you added.
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 · 31 lines · 46 tokens per session scan A 23344ce7a973
debugger is an agent published in the GitHub repository dshakes/compass (19 stars, last pushed 8d ago), licensed MIT. It adds 46 tokens to every session and 426 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.