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 jnPiyush/AgentX --skill systematic-debugginggit clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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/jnpiyush/agentx/systematic-debugging)<a href="https://agentmods.dev/skills/jnpiyush/agentx/systematic-debugging"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/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/jnpiyush/agentx/systematic-debugging"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/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 | $0.00068 | $0.01624 |
| Opus 5.5 | $0.00027 | $0.00650 |
| Sonnet 5.5 | $0.00014 | $0.00325 |
| Haiku 4.5 | $0.00007 | $0.00162 |
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 1mo 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging
WHEN: A bug fix has failed two or more times, the same test keeps failing for different reasons, or the symptom keeps moving when fixes are applied. Also use proactively for any
type:bugthat touches more than one file or crosses a module boundary.
When to Use This Skill
Load this skill when:
- Two or more fixes for the same bug have not held
- The failing test now fails in a different way after each attempt
- A
type:bugissue is non-trivial (more than a single-file typo) - A Reviewer has issued
CHANGES REQUESTEDtwice on the same defect - You feel the urge to "try one more thing" instead of investigating
Skip when:
- The bug is a single-line obvious typo with no dependencies
- The failure mode is fully understood and the fix is mechanical
Prerequisites
- Reproduction of the bug, or a failing test that captures it
- Access to the relevant logs, stack traces, and recent commits
- Time budget; this skill is slower than guess-and-fix, on purpose
Rationalization Table
The three-failed-fixes rule exists because LLMs and humans both reach for these instead of investigating.
| Rationalization | Reality |
|---|---|
| "Let me try one more small change, it might work." | Three failed fixes is the signal that you do not understand the bug. Stop changing code; investigate. |
| "I know what's wrong, I just need to fix it." | If you knew, the first fix would have worked. Treat the failed fixes as evidence that the model is wrong. |
| "The stack trace points right at this line." | The stack trace points at the symptom. The cause is usually somewhere else in the call graph or in state set up earlier. |
| "I'll add a try/catch and move on." | Suppressing the error does not fix the bug; it hides it. The next failure will be harder to find. |
| "This bug is too weird, I'll work around it." | Workarounds compound. The next person to hit this pays the cost. Fix the cause. |
| "It works locally, must be an environment issue." | "Works on my machine" is a hypothesis, not a conclusion. Verify the environment difference is the actual cause. |
| "I'll revert and start over with a fresh approach." | Reverting without root cause loses evidence. Investigate first, then decide whether to revert. |
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.
- 1mo ago Changed e2b8a8bf69f6
- 1mo ago First seen · 142 lines · 68 tokens per session scan A ed0120c819ca
systematic-debugging is a skill published in the GitHub repository jnPiyush/AgentX (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,624 once invoked, about $0.0003 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 2026-09-03.
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…