systematic-debugging

systematic-debugging is a skill for Claude Code, Codex from metaspartan/cybara. It costs 40 tokens per session (430 once invoked), scanned A, original, MIT.

A structured method for finding the root cause of a bug, crash, failed test, or unexpected result. It reproduces the problem, isolates its trigger, tests one explanation, and verifies the fix.

In plain words
What is it for?
Use it to investigate software failures, add a regression test, and rerun the affected test suite after fixing the underlying cause.
Why use it?
It prevents symptom-based changes and makes it less likely that a fix will regress or fail in related cases.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/metaspartan/cybara/systematic-debugging
Any agent
npx skills add metaspartan/cybara --skill systematic-debugging
Clone the repo
git clone --depth 1 https://github.com/metaspartan/cybara

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for systematic-debugging

README.md
[![agentmods](https://agentmods.dev/badge/skills/metaspartan/cybara/systematic-debugging.svg)](https://agentmods.dev/skills/metaspartan/cybara/systematic-debugging)
Your own site
<a href="https://agentmods.dev/skills/metaspartan/cybara/systematic-debugging"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/systematic-debugging.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 430 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.00430
Opus 5 $0.00020 $0.00215
Sonnet 5 $0.00008 $0.00086
Haiku 4.5 $0.00004 $0.00043

Measured yesterday against content hash 7e2468e80cc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

skills/systematic-debugging/SKILL.md · 34 lines

What it actually says

Systematic Debugging

A disciplined loop that finds the true root cause before changing code. Skipping it is the #1 cause of "fixes" that regress or don't hold.

The loop

  1. Reproduce reliably. Get a minimal, repeatable repro (command, input, test). If you can't reproduce it, say so and gather more info before touching code.
  2. Read the error fully. Capture the exact message, stack trace, and the line it points to. Don't guess from a summary.
  3. Isolate. Narrow the trigger: which input, which code path, which environment/version? Binary-search with logs or by disabling code.
  4. Form ONE hypothesis about the root cause. State it explicitly: "I think X happens because Y."
  5. Verify the hypothesis with the cheapest probe: a log, a print, a test, a debugger breakpoint (lsp_diagnostics, exec with a tiny script). Confirm before fixing.
  6. Fix the root cause, not the symptom. The fix should make the repro pass AND not break related cases.
  7. Add a regression test that captures the repro, so it can't come back.
  8. Re-run the full affected test suite, not just the one case.

Anti-patterns to avoid

  • Changing multiple things at once → you won't know which fixed it.
  • "Fixing" by catching/swallowing the error.
  • Editing code based on a guess without confirming the hypothesis.
  • Declaring fixed without re-running the repro.

When stuck

  • Re-read the original repro; assumptions drift.
  • Search code (grep) and the issue for similar symptoms.
  • Check recent changes (git log, git diff) — regressions usually track recent edits.
  • Form a NEW hypothesis; don't keep retesting the same one.
Changes

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.

  1. yesterday First seen · 34 lines · 40 tokens per session scan A 7e2468e80cc4

Subscribe to this mod's changes

systematic-debugging is a skill published in the GitHub repository metaspartan/cybara (25 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 430 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.