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 EzraApple/skills-init --skill systematic-debugginggit clone --depth 1 https://github.com/EzraApple/skills-initWrote 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/ezraapple/skills-init/systematic-debugging)<a href="https://agentmods.dev/skills/ezraapple/skills-init/systematic-debugging"><img src="https://agentmods.dev/badge/skills/ezraapple/skills-init/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/ezraapple/skills-init/systematic-debugging"><img src="https://agentmods.dev/badge/skills/ezraapple/skills-init/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 | $0.00028 | $0.00375 |
| Opus 5.5 | $0.00011 | $0.00150 |
| Sonnet 5.5 | $0.00006 | $0.00075 |
| Haiku 4.5 | $0.00003 | $0.00038 |
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 18d 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.
What it actually says
Systematic debugging
Treat a plausible explanation as a hypothesis until evidence distinguishes it from competing causes. Diagnosis alone does not authorize a fix.
Establish the expected result, observed failure, triggering input, environment, and last known good state when available. Separate the reported symptom from the reporter's proposed explanation.
Find the first divergence
Reproduce on the failing surface, or identify the strongest available evidence and its limits. Trace backward from the wrong result through actual callers, state changes, and boundaries. Locate the earliest point where an invariant fails, rather than the last place an exception appears.
When several causes fit, record what would distinguish them and run the cheapest discriminating probe. Keep evidence that ruled a cause out. If repeated attempts fail, question the shared premise or improve the observation method before adding another workaround.
- For measured speed or resource claims, read benchmarks.md.
- For CPU profiles, traces, or heap captures, read runtime-artifacts.md.
Repair and verify
When fixes are requested, change the boundary that owns the violated invariant. Avoid adding retries, delays, or guards unless they implement the actual contract. Preserve unrelated behavior and external compatibility.
If an existing local test can cheaply capture the defect, show it failing for the intended reason before the fix and passing afterward. Otherwise use the closest stable reproduction; do not build a broad test harness for ceremony.
Rerun the original failing path and the nearby path implicated by the cause. For intermittent failures, compare repeated observations. Report the mechanism, evidence, repair or recommendation, and any environment still unverified.
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.
- 18d ago Changed · -66 lines · -26 tokens per session c724d3901bb2
- 2mo ago First seen · 109 lines · 54 tokens per session scan A bbe3ce67cf83
systematic-debugging is a skill published in the GitHub repository EzraApple/skills-init (2 stars, last pushed 19d ago), licensed MIT. It adds 28 tokens to every session and 375 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
kiro-verify-completion
Verify completion and success claims with fresh evidence. Use before claiming a task is complete, a fix works, tests pass, or a feature is ready for GO.
diagnose-backend-bug
Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do…
prismer-python-debugpy
Debug Python: pdb REPL + debugpy remote (DAP).
debug-live
Guides root-cause investigations with debugging capabilities by setting breakpoints, starting a debug session, stepping through execution, inspecting variables, and tracing symptoms back to their origin. Prefer it for runtime bugs, failing tests, exceptions, crashes, hangs, wrong/null values, and unexpected output…
dsh-error-handling
A workflow for designing and reviewing how software reports errors, partial success, unknown results, recovery, retries, cancellation, and failure feedback.
remove-deadcode
Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits. Triggers: remove dead code, dead code, cleanup, remove unused.