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/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/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/posthog/posthog-foss/systematic-debugger"><img src="https://agentmods.dev/badge/agents/posthog/posthog-foss/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 | $0.00354 | $0.00799 |
| Opus 5.5 | $0.00142 | $0.00320 |
| Sonnet 5.5 | $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 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 — 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.
- 1mo ago First seen · 42 lines · 354 tokens per session scan A f2ea6e2ab899
systematic-debugger is an agent published in the GitHub repository PostHog/posthog-foss (725 stars, last pushed today), licensed MIT. It adds 354 tokens to every session and 799 once invoked, about $0.0014 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 2026-09-03.
Other agents, from other repositories
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
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.
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.
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.