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 skills add hoangatg/ai-agent-toolkit --skill systematic-debugginggit clone --depth 1 https://github.com/hoangatg/ai-agent-toolkitWrote 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/skills/hoangatg/ai-agent-toolkit/systematic-debugging)<a href="https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/systematic-debugging"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/systematic-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/skills/hoangatg/ai-agent-toolkit/systematic-debugging"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/systematic-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 | $0.00025 | $0.00610 |
| Opus 5 | $0.00013 | $0.00305 |
| Sonnet 5 | $0.00005 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
systematic-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 8d 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.
This is a copy
89% identical to systematic-debugging — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging
Source: obra/superpowers
Overview
This skill provides a structured approach to debugging that prevents random guessing and ensures problems are properly understood before solving.
4-Phase Debugging Process
Phase 1: Reproduce
Before fixing, reliably reproduce the issue.
## Reproduction Steps
1. [Exact step to reproduce]
2. [Next step]
3. [Expected vs actual result]
## Reproduction Rate
- [ ] Always (100%)
- [ ] Often (50-90%)
- [ ] Sometimes (10-50%)
- [ ] Rare (<10%)
Phase 2: Isolate
Narrow down the source.
## Isolation Questions
- When did this start happening?
- What changed recently?
- Does it happen in all environments?
- Can we reproduce with minimal code?
- What's the smallest change that triggers it?
Phase 3: Understand
Find the root cause, not just symptoms.
## Root Cause Analysis
### The 5 Whys
1. Why: [First observation]
2. Why: [Deeper reason]
3. Why: [Still deeper]
4. Why: [Getting closer]
5. Why: [Root cause]
Phase 4: Fix & Verify
Fix and verify it's truly fixed.
## Fix Verification
- [ ] Bug no longer reproduces
- [ ] Related functionality still works
- [ ] No new issues introduced
- [ ] Test added to prevent regression
Debugging Checklist
## Before Starting
- [ ] Can reproduce consistently
- [ ] Have minimal reproduction case
- [ ] Understand expected behavior
## During Investigation
- [ ] Check recent changes (git log)
- [ ] Check logs for errors
- [ ] Add logging if needed
- [ ] Use debugger/breakpoints
## After Fix
- [ ] Root cause documented
- [ ] Fix verified
- [ ] Regression test added
- [ ] Similar code checked
Common Debugging Commands
# Recent changes
git log --oneline -20
git diff HEAD~5
# Search for pattern
grep -r "errorPattern" --include="*.ts"
# Check logs
pm2 logs app-name --err --lines 100
Anti-Patterns
❌ Random changes - "Maybe if I change this..." ❌ Ignoring evidence - "That can't be the cause" ❌ Assuming - "It must be X" without proof ❌ Not reproducing first - Fixing blindly ❌ Stopping at symptoms - Not finding root cause
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.
- 8d ago First seen · 110 lines · 25 tokens per session scan A 53b60eed01a4
systematic-debugging is a skill published in the GitHub repository hoangatg/ai-agent-toolkit (1 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 610 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to systematic-debugging, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
issue-root-resolution
Trigger: root audit, atacar la raíz, issue roots, backlog roots, mechanism map, deletion-driven fix, resolver issues de raíz, close outdated issues. Audit and resolve issue clusters by verified root cause.
rdd-defect-workflow
Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
incident-response
Incident management lifecycle — triage, communicate, mitigate, postmortem. Three modes — new (start incident), update (status update), postmortem (blameless RCA report).
ctxo-safe-edit
Use BEFORE editing, renaming, or deleting any function, class, or method, to avoid breaking dependents.