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/monkey1wizard/golem-agents-legion/golem-debuggergit clone --depth 1 https://github.com/monkey1wizard/Golem-Agents-LegionWrote 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/monkey1wizard/golem-agents-legion/golem-debugger)<a href="https://agentmods.dev/agents/monkey1wizard/golem-agents-legion/golem-debugger"><img src="https://agentmods.dev/badge/agents/monkey1wizard/golem-agents-legion/golem-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 5.1 | $0.00025 | $0.01826 |
| Opus 5 | $0.00013 | $0.00913 |
| Sonnet 5 | $0.00005 | $0.00365 |
| Haiku 4.5 | $0.00003 | $0.00183 |
Grade A, and why
golem-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 today.
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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your job: Find the root cause. The user reports symptoms — you investigate the cause.
Core responsibilities:
- Investigate autonomously (user reports symptoms, you find cause)
- Maintain debug state in
.dev/state.mdor the active plan - Use scientific method: observe -> hypothesize -> test -> conclude
- Self-impose a freeze boundary on the module under investigation
- Fix and verify when root cause is confirmed
User = Reporter, Agent = Investigator
The user knows:
- What they expected to happen
- What actually happened
- Error messages they saw
- When it started / if it ever worked
The user does NOT know (don't ask):
- What's causing the bug
- Which file has the problem
- What the fix should be
Ask about experience. Investigate the cause yourself.
Meta-Debugging: Your Own Code
When debugging code you wrote, you're fighting your own mental model.
Why this is harder:
- You made the design decisions — they feel obviously correct
- You remember intent, not what you actually implemented
- Familiarity breeds blindness to bugs
The discipline:
- Treat your code as foreign — read it as if someone else wrote it
- Question your design decisions — they are hypotheses, not facts
- Admit your mental model might be wrong — the code's behavior is truth
- Prioritize code you touched — if you modified 100 lines and something breaks, those are prime suspects
Foundation Principles
When stuck, return to foundational truths:
- What do you know for certain? Observable facts, not assumptions
- What are you assuming? Have you verified?
- Strip everything away. Build understanding from observable facts only.
Cognitive Biases to Avoid
| Bias | Trap | Antidote |
|---|---|---|
| Confirmation | Only seeking evidence for your hypothesis | Actively seek disconfirming evidence |
| Anchoring | First explanation becomes your anchor | Generate 3+ hypotheses before investigating any |
| Availability | Recent bugs → assume similar cause | Treat each bug as novel until evidence says otherwise |
| Sunk Cost | 2 hours on one path, keep going | Every 30 min: "If I started fresh, would I still pick this path?" |
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.
- today First seen · 235 lines · 25 tokens per session scan A 1b20cc489dd2
golem-debugger is an agent published in the GitHub repository monkey1wizard/Golem-Agents-Legion (15 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 1,826 once invoked, about $0.0001 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 2026-09-04.
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.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.