Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add MadAppGang/magus/plugin install devWrote 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/madappgang/magus/systematic-debugging)<a href="https://agentmods.dev/skills/madappgang/magus/systematic-debugging"><img src="https://agentmods.dev/badge/skills/madappgang/magus/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/madappgang/magus/systematic-debugging"><img src="https://agentmods.dev/badge/skills/madappgang/magus/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 | $0.00055 | $0.00699 |
| Opus 5.5 | $0.00022 | $0.00280 |
| Sonnet 5.5 | $0.00011 | $0.00140 |
| Haiku 4.5 | $0.00006 | $0.00070 |
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 22d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging
One entry point for finding why code is wrong. Read the section you need; each links to a sibling file with the full detail.
The rule
No fix without a root cause. If you cannot say which line produces the wrong value and why, you are guessing. A guess that happens to work is a latent bug — it will come back wearing different symptoms.
Red flags that you have skipped the diagnosis: changing code to "see if it helps", adding defensive checks around a symptom, fixing the same area twice, or being unable to explain why the fix works.
Pick a depth
| Situation | Do this |
|---|---|
| Obvious cause, one file, low risk | Fix inline. No ceremony. |
| Needs investigation, unclear origin | Follow workflow.md |
| Production-critical, intermittent, or uncertain | Run /dev:fix — full TDD with review gates |
/dev:debug routes between these three for you.
The four phases
- Reproduce — a failing case you can run on demand. Without this you cannot tell a fix from a coincidence.
- Localize — narrow to the specific code producing the wrong value.
Strategies in
localization.md. - Explain — state the mechanism: this input, through this path, yields this wrong output. Then predict what changing it will do.
- Verify — the reproduction now passes, and you can say why. Re-run the surrounding tests; a fix that breaks a neighbour was the wrong fix.
Full walkthrough with output schemas: workflow.md.
Reference files
| File | Contents |
|---|---|
method.md |
Principles, red flags, hypothesis discipline, strategies by problem type (performance, intermittent, regression, integration) |
workflow.md |
The phase-by-phase standard workflow with report schemas |
localization.md |
Three fault-localization strategies — stack-trace grep, BM25 keyword search, AST context expansion — plus context-budget rules and the large-codebase path |
session-setup.md |
Session directory layout, stack detection, reproduction capture, bug-report schema. Shared by /dev:debug and /dev:fix. |
references/techniques.md |
The technique catalogue — stack-trace reading, error categories, wolf fence, data-flow tracing, logging, breakpoints, plus browser and Node.js specifics |
What ships with it
5 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.
- 22d ago Changed 2832b7d8d83a
- 1mo ago First seen · 63 lines · 55 tokens per session scan A 914d8fde4811
systematic-debugging is a skill published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 699 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…