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/kyungseo/ai-workflow-harnessWrote 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/rules/kyungseo/ai-workflow-harness/debugging)<a href="https://agentmods.dev/rules/kyungseo/ai-workflow-harness/debugging"><img src="https://agentmods.dev/badge/rules/kyungseo/ai-workflow-harness/debugging/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/rules/kyungseo/ai-workflow-harness/debugging"><img src="https://agentmods.dev/badge/rules/kyungseo/ai-workflow-harness/debugging.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 | $0.00016 | $0.00252 |
| Opus 5.5 | $0.00006 | $0.00101 |
| Sonnet 5.5 | $0.00003 | $0.00050 |
| Haiku 4.5 | $0.00002 | $0.00025 |
Grade A, and why
debugging 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.
What it actually says
Debugging Rules
MUST follow this sequence:
- Reproduce or clearly describe the failing condition.
- Narrow the cause using actual code, logs, stack traces, tests, or runtime output.
- Fix the ROOT CAUSE with the smallest reasonable change.
- Re-run the same scenario or test that exposed the issue.
MUST NOT:
- Guess the cause without evidence.
- Mask a failure by weakening assertions, deleting tests, or broadening exception handling.
- Change unrelated behavior while debugging.
When a test fails, explain:
- The failing scenario.
- The most likely root cause.
- The verification command or scenario used after the fix.
When a non-trivial issue is fully resolved (environment mismatch, hidden constraint, non-obvious root cause, tool version incompatibility), record it in docs/troubleshooting/ using the symptom → cause → action format. Apply the DR-027 frontmatter spec (symptom/track/category/environment/status/related_dr). Link from docs/HARNESS-MAINTAINER-GUIDE.md if the issue affects local setup.
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 · 29 lines · 16 tokens per session scan A 1ab612251f83
debugging is a cursor rule published in the GitHub repository kyungseo/ai-workflow-harness (14 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 252 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 cursor rules, from other repositories
minimax-m3-verification
Extended M3 verification playbook: proof selection, multimodal-grounded checks, shell checks, browser checks, and recovery loops.
minimax-m3-self-evolution
MiniMax M3 self-evolution harness: iterative refinement loops, compress-before-iterate, autonomous debugging, and recursive improvement patterns.
analyze-failures
Triage Katalon True Platform/TestOps test failures and file defects. Use when you need to investigate failed test results, classify each failure as product defect vs automation defect vs environment/data issue, cluster failures by common signature, find likely root cause from execution data, and optionally create…
miru-code-search
Miru MCP is the default for conceptual code exploration.
language-agnostic-patterns
Language-agnostic programming patterns: SOLID, design patterns, clean code, and architecture. Load when refactoring, designing abstractions, or reviewing structure — not for everyday syntax.
cursor-tools-mastery
Cursor 3.7 runtime guide: choose the right tool, canvases, Design Mode, /worktree, /best-of-n, Await, and parallel execution where safe.