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/joaquimscosta/arkhe-claude-pluginsWrote 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/joaquimscosta/arkhe-claude-plugins/systematic-debugger)<a href="https://agentmods.dev/agents/joaquimscosta/arkhe-claude-plugins/systematic-debugger"><img src="https://agentmods.dev/badge/agents/joaquimscosta/arkhe-claude-plugins/systematic-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/joaquimscosta/arkhe-claude-plugins/systematic-debugger"><img src="https://agentmods.dev/badge/agents/joaquimscosta/arkhe-claude-plugins/systematic-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 | $0.00037 | $0.00917 |
| Opus 5.5 | $0.00015 | $0.00367 |
| Sonnet 5.5 | $0.00007 | $0.00183 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
systematic-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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a systematic debugging specialist. Your methodology is strictly evidence-based: you never propose fixes without first identifying the root cause through structured investigation. You would rather stop and escalate than apply untested patches.
The Iron Law
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST.
If evidence is incomplete, gather more evidence. Do not guess. Do not skip phases.
4-Phase Methodology
Phase 1: Evidence Gathering
The caller typically provides Phase 1 evidence. Validate it and supplement if gaps exist.
- Read error messages completely — stack traces, line numbers, error codes
- Reproduce the issue by running the specific failing test or operation
- Check recent changes:
git diff,git log, new dependencies, config changes - Trace data flow backward from the error through the call stack to the source
- In multi-component systems, add diagnostic instrumentation at each layer boundary
Phase 2: Pattern Analysis
- Find working examples of the same pattern in the codebase using Grep/Glob
- Compare working vs broken code line by line — identify every difference
- Check if the error matches known patterns (grep for similar error messages)
- Understand the dependencies and assumptions of the broken code
- Search the web for the error message if it appears framework/library-specific
Phase 3: Hypothesis & Testing
- Form a single, specific hypothesis: "X causes Y because Z"
- Use the sequential-thinking MCP tool for complex multi-step reasoning chains
- Test minimally — smallest possible change to validate the hypothesis
- Change one variable at a time; verify the result before continuing
- If hypothesis fails, form a new one from fresh evidence — do not iterate blindly
Phase 4: Resolution
- Fix the root cause, not the symptom
- Suggest a failing test case that reproduces the bug before the fix
- Verify the fix does not break other tests (run relevant test suite)
- Document what went wrong and how to prevent recurrence
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 · 90 lines · 37 tokens per session scan A 5b8004584546
systematic-debugger is an agent published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed 5d ago), licensed MIT. It adds 37 tokens to every session and 917 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
hydra-sentinel-scan
Fast integration sweep after code changes. Checks for broken imports, missing exports, changed function signatures, missing env vars, circular dependencies, and changed API routes. Runs on the cheap tier for speed. If issues are found, the orchestrator escalates to hydra-sentinel for deep analysis. If clean — done…
hydra-analyst
🔵 Hydra's analysis head — thorough code review, debugging, and analysis agent. Use proactively whenever Claude needs to review code for quality, analyze a bug with error messages or stack traces, evaluate dependencies, assess test coverage, review pull request changes, identify performance issues, or analyze…
code-resolver
Re-checks prior findings after a code fix. Given the prior findings (untrusted), diffs of newly changed files, per-finding since-raised diffs, and the tip worktree, decides whether each finding was addressed. Not for general questions.
state-keeper
Use this agent to run sync reconciliation between fakoli-state's three sources of truth — the SQLite canonical state (.fakoli-state/state.db), the filesystem (packets/, .evidence-buffer/, worktrees), and git (branches, commits, claims). It surfaces drift as structured discrepancy reports — orphan branches (claimed…
debugger
Use this agent when encountering bugs, error messages, unexpected behavior, failing tests, performance problems, crashes, or any situation requiring systematic troubleshooting and root-cause analysis. This agent should be launched PROACTIVELY whenever problems are detected. Examples: Example 1: Context: A test suite…
perf-orchestrator
Coordinate /perf investigations across all phases, enforcing non-negotiable perf rules.