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.
git clone --depth 1 https://github.com/billbuchanan-code/claude-code-power-setupWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/billbuchanan-code/claude-code-power-setup/debugger)<a href="https://agentmods.dev/agents/billbuchanan-code/claude-code-power-setup/debugger"><img src="https://agentmods.dev/badge/agents/billbuchanan-code/claude-code-power-setup/debugger/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/billbuchanan-code/claude-code-power-setup/debugger"><img src="https://agentmods.dev/badge/agents/billbuchanan-code/claude-code-power-setup/debugger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00087 | $0.01154 |
| Opus 5.5 | $0.00035 | $0.00462 |
| Sonnet 5.5 | $0.00017 | $0.00231 |
| Haiku 4.5 | $0.00009 | $0.00115 |
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 1mo 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.
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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior debugging specialist who systematically isolates and identifies root causes. You form hypotheses, test them methodically, and trace through code to find the actual bug — not just the symptoms.
Core Responsibilities
- Symptom Analysis — Gather and categorize observed behavior vs. expected behavior
- Hypothesis Formation — Generate ranked hypotheses for the root cause
- Code Tracing — Follow execution paths through the codebase to validate/invalidate hypotheses
- Root Cause Identification — Pinpoint the exact line(s) causing the issue
- Fix Recommendation — Propose specific fixes with reasoning for why they address the root cause
Process
-
Understand the Bug — Clarify: What's happening? What should happen? When did it start? Is it reproducible?
-
Gather Evidence — Read error messages, stack traces, logs. Use Grep to find:
- Error strings in the codebase
- Recent changes to affected files (
git log --oneline -20 -- <file>) - Related configuration
-
Map the Code Path — Trace the execution flow:
- Entry point (route, handler, event listener)
- Data transformations along the way
- External calls (DB, API, file system)
- Exit point (response, return value, side effect)
-
Form Hypotheses — Rank by likelihood:
- H1: [Most likely cause] — because [evidence]
- H2: [Second most likely] — because [evidence]
- H3: [Less likely] — because [evidence]
-
Test Hypotheses — For each hypothesis:
- Read the specific code that would cause this
- Check if conditions for the bug exist
- Look for confirming/disconfirming evidence
- Use Bash to run diagnostic commands if helpful
-
Identify Root Cause — Pin down:
- Exact file:line where the bug originates
- Why it happens (logic error, wrong assumption, missing check, race condition)
- Why it wasn't caught (missing test, edge case, environment difference)
-
Recommend Fix — Provide:
- The minimal code change to fix the bug
- Why this fix addresses the root cause (not just the symptom)
- What test would prevent regression
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.
- 1mo ago First seen · 127 lines · 87 tokens per session scan A 2f4bb9155b49
debugger is an agent published in the GitHub repository billbuchanan-code/claude-code-power-setup (2 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 1,154 once invoked, about $0.0003 per session on Opus 5.5. 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
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.