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 majiayu000/spellbook --skill systematic-debugginggit clone --depth 1 https://github.com/majiayu000/spellbookWrote 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/majiayu000/spellbook/systematic-debugging)<a href="https://agentmods.dev/skills/majiayu000/spellbook/systematic-debugging"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/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/majiayu000/spellbook/systematic-debugging"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/systematic-debugging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.00926 |
| Opus 5 | $0.00015 | $0.00463 |
| Sonnet 5 | $0.00006 | $0.00185 |
| Haiku 4.5 | $0.00003 | $0.00093 |
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.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging
From obra/superpowers
Core Principle
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
Random fixes create new bugs. Understanding must precede solutions.
The Four Phases
Phase 1: Root Cause Investigation
Before ANY fix attempt:
-
Read error messages carefully
- Full stack traces
- Error codes and descriptions
- Timestamps and context
-
Reproduce consistently
- Document exact steps
- Identify triggers
- Note environmental factors
-
Check recent changes
- Recent commits
- Dependency updates
- Configuration changes
-
Gather diagnostic evidence
- Add logging at component boundaries
- Check input/output at each step
- Trace data flow backward to source
Phase 2: Pattern Analysis
-
Find similar working code
- Search codebase for related functionality
- Look for existing patterns
-
Read reference implementations completely
- Don't skim
- Understand the full context
-
Compare working vs broken
- What's different?
- What assumptions changed?
-
Understand dependencies
- What does this code rely on?
- What relies on this code?
Phase 3: Hypothesis and Testing
-
Form a SINGLE, SPECIFIC hypothesis
- "The error occurs because X"
- Not "maybe it's A or B or C"
-
Test with minimal changes
- One variable at a time
- Don't combine fixes
-
Accept results
- If hypothesis is wrong, form new one
- Don't force-fit evidence
-
Ask for help when stuck
- After genuine investigation
- With evidence gathered
Phase 4: Implementation
-
Create a failing test case FIRST
- Reproduces the bug
- Will pass when fixed
-
Implement SINGLE fix
- Address root cause only
- Don't fix "nearby" issues
-
Verify the fix
- Test case passes
- No regressions
- Issue is resolved
The 3-Fix Rule
If ≥3 fixes fail: STOP and question the architecture
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 · 166 lines · 31 tokens per session scan A 9b84f2e1da7d
systematic-debugging is a skill published in the GitHub repository majiayu000/spellbook (278 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 926 once invoked, about $0.0002 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 skills, from other repositories
workflow
A workflow skill for embedded-device projects that plans and runs building, flashing, debugging, observing, and diagnosis tasks.
pneuma-session
Instructions for renaming an active Pneuma session and replacing its default preview with a useful title and summary. A Pneuma session is one work area inside a larger project.
cheese
Route an idea, path, pull request, issue, failure, question, or bare /cheese to the correct workflow skill. Use this skill for /cheese, routing requests, help requests, or opening messages without a named workflow skill.
joycraft-bugfix
Structured bug fix workflow — triage, diagnose, discuss with user, write a focused spec, hand off for implementation.
happy-handoff
A workflow for moving an unfinished Codex Desktop task to Happy on Android at a safe checkpoint. It records the workspace state and next step before starting the resumed session.
x-bug2rag
A knowledge-capture tool that turns reusable bug explanations into a local RAG collection, meaning a searchable store of text that an agent can retrieve later. It records the trigger, incorrect implementation, correct implementation, and observable difference.