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 skills/sangrokjung/claude-forge/systematic-debuggingnpx skills add sangrokjung/claude-forge --skill systematic-debugginggit clone --depth 1 https://github.com/sangrokjung/claude-forgeWrote 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/sangrokjung/claude-forge/systematic-debugging)<a href="https://agentmods.dev/skills/sangrokjung/claude-forge/systematic-debugging"><img src="https://agentmods.dev/badge/skills/sangrokjung/claude-forge/systematic-debugging.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 | $0.00053 | $0.01744 |
| Opus 5 | $0.00026 | $0.00872 |
| Sonnet 5 | $0.00011 | $0.00349 |
| Haiku 4.5 | $0.00005 | $0.00174 |
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 2d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging
Overview
Guessing fixes wastes time and creates new bugs. Quick patches hide root problems.
Core principle: Never fix before finding the root cause. Symptom fixing is failure.
Iron Law
Never propose a fix without root cause investigation.
Phase 0 or Phase 1 must be completed before any fix is proposed. Phase 0 fixes are ONLY allowed when ALL of these are true:
- External research found an official solution or known issue for this exact error
- Change is single file, single point (config value, import, typo)
- No logic changes
When to Use
All technical problems:
- Test failures, build errors, deploy errors
- Config conflicts, dependency issues
- Infrastructure/environment problems
- Unexpected behavior, performance issues
Especially when:
- Under time pressure (urgency breeds guessing)
- "Let me just quickly fix this" comes to mind
- Multiple fix attempts have already been tried
- Previous fixes didn't work
- You don't fully understand the problem
The Phases
Each Phase must complete before proceeding to the next.
Phase 0: Quick Assessment
Run immediately when an error occurs. Before any fix attempt.
-
Classify the error — read the error message/symptoms:
- Same code works in different environment? → Environment issue
- After recent dependency/version change? → Dependency issue
- Only fails in specific code path? → Code issue
-
External research (exact match, 5 min max) — check official docs and GitHub Issues for known issues. Don't rely on self-knowledge alone.
- See:
references/external-research-guide.md
- See:
-
Branch decision:
- All Iron Law conditions met → Fix in Phase 0
- Any condition unmet → Enter Phase 1 full process
- Phase 0 quick-fix fails: Undo (git checkout/undo), enter Phase 1. This attempt counts in the fix counter.
Phase 1: Root Cause Investigation
Before any fix attempt:
- Read the error carefully
- Don't skip errors/warnings
- Read the entire stack trace
- Record line numbers, file paths, error codes
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 188 lines · 53 tokens per session scan A 5d93c80e8f3a
systematic-debugging is a skill published in the GitHub repository sangrokjung/claude-forge (824 stars, last pushed 3d ago), licensed MIT. It adds 53 tokens to every session and 1,744 once invoked, about $0.0003 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
debug-systematic
Systematic 4-phase debugging methodology for complex, intermittent, or mysterious issues. Use when investigating bugs, race conditions, or unexplained failures.
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
incident-brief-generator
Builds a concise incident handoff from symptoms, health evidence, and logs.
eval-rules
Audit .claude/rules/ files for structural correctness, glob validity, and real-world usefulness. Resolves each paths: pattern against actual project files, then asks the user whether each rule is still relevant and useful. Can update rules in-place based on answers. Use when setting up rules for the first time…
system-health-snapshot
Use this bundled starter skill to read Friday's current runtime snapshot and summarize.