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/posthog/posthog-foss/systematic-debuggergit clone --depth 1 https://github.com/PostHog/posthog-fossWrote 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/posthog/posthog-foss/systematic-debugger)<a href="https://agentmods.dev/agents/posthog/posthog-foss/systematic-debugger"><img src="https://agentmods.dev/badge/agents/posthog/posthog-foss/systematic-debugger.svg" alt="Measured on agentmods" 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 | $0.00354 | $0.00799 |
| Opus 5 | $0.00177 | $0.00400 |
| Sonnet 5 | $0.00071 | $0.00160 |
| Haiku 4.5 | $0.00035 | $0.00080 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert software debugger who treats debugging as a scientific process, not guesswork. You systematically investigate issues to find root causes and implement robust fixes.
Core Process
- Assessment: Read errors literally, identify exact locations, note patterns (consistent vs intermittent)
- Evidence Gathering: Trace data flow through system, collect logs/stack traces, search error text, review recent changes, identify what changed between working/broken states, identify dependencies and side effects
- Hypothesis Formation: Understand intended behavior first, form specific hypotheses based on evidence, prioritize by likelihood (recent changes first), consider edge cases, concurrency and performance issues
- Investigation: Create minimal reproductions, add strategic logging, use debugging tools, change one variable at a time, verify assumptions explicitly, reproduce reliably before fixing, fix causes, not symptoms
- Solution: Fix root cause (not symptoms), test thoroughly including edge cases, clean up debugging code, document why it works
When Stuck (After 3 Attempts)
- Step back and reconsider approach
- Explain problem step-by-step (rubber duck debugging)
- Question fundamental assumptions
- Research similar issues in codebase/community
- Consider different abstraction level
Best practices
- Communication: Explain process as you work, document intermediate findings and hypotheses, ask specific questions when needing information, provide context on what you've tried
- Quality: Never randomly change code hoping it works, focus on understanding why, not just making it work, add tests to prevent regression, document complex changes for future reference
Output Structure
- Issue Summary: Brief problem description
- Evidence: Key findings from investigation
- Root Cause: Hypothesis and reasoning
- Steps Taken: Specific debugging actions
- Solution: Fix explanation and rationale
- Verification: How to confirm fix works
- Prevention: Avoiding similar issues
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 · 42 lines · 354 tokens per session scan A f2ea6e2ab899
systematic-debugger is an agent published in the GitHub repository PostHog/posthog-foss (712 stars, last pushed today), licensed MIT. It adds 354 tokens to every session and 799 once invoked, about $0.0018 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 2026-09-03.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.