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 jnMetaCode/skillet --skill systematic-debugginggit clone --depth 1 https://github.com/jnMetaCode/skilletWrote 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/jnmetacode/skillet/systematic-debugging)<a href="https://agentmods.dev/skills/jnmetacode/skillet/systematic-debugging"><img src="https://agentmods.dev/badge/skills/jnmetacode/skillet/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/jnmetacode/skillet/systematic-debugging"><img src="https://agentmods.dev/badge/skills/jnmetacode/skillet/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 | $0.00043 | $0.00532 |
| Opus 5.5 | $0.00017 | $0.00213 |
| Sonnet 5.5 | $0.00009 | $0.00106 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
systematic-debugging scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
line, an assertion, a debugger breakpoint, one curl. What it actually says
systematic-debugging
Never fix what you can't reproduce; never explain what you haven't observed. The loop is: reproduce → observe → hypothesize → test the hypothesis → narrow. One variable at a time.
Procedure
- Reproduce first. Find the smallest, fastest command that shows the
failure deterministically. If it's flaky, make the loop tight
(
while ./repro; do :; done) and treat flakiness itself as a clue (timing, ordering, shared state). - Read the actual error. The full message, the first stack frame in your own code, and the line right before things went wrong. Resist pattern-matching to a familiar failure — verify this one.
- State a falsifiable hypothesis ("the cache returns stale entries after a restart") and pick the cheapest observation that could kill it: a log line, an assertion, a debugger breakpoint, one curl.
- Bisect the space, whichever axis is cheapest:
- history:
git bisect run ./repro - data: half the failing input, recurse
- stack: confirm the bad value at the boundary between two layers, then descend into the guilty one only
- history:
- The fix must explain the symptom. Before writing it, say why this cause produces exactly this behavior. If the explanation is fuzzy, you've found a bug, maybe not the bug.
- Prove it: the repro from step 1 now passes, AND a new regression test
fails without the fix. Then look for siblings — the same mistake usually
exists elsewhere (
grepfor the pattern you just fixed).
Anti-patterns
- Changing two things between observations — you learn nothing from the result.
- "It works now" without knowing why it failed — it will be back.
- Adding sleeps to fix timing issues — that's hiding the race, not fixing it.
- Debugging through the framework before confirming your own code's inputs and outputs at the boundary.
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 First seen · 46 lines · 43 tokens per session scan A 8d9f567283a4
systematic-debugging is a skill published in the GitHub repository jnMetaCode/skillet (2 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 532 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
credit-note-fixer
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
resolve-author-fix
Find the root cause, implement a focused fix, and prove behavior with targeted tests and recordings.
resolve-repro-audit
Audit a recovered repro patch, assertions, and behavioral baseline before authoring or reviewing.
error-analysis
Evals-first error analysis for LLM apps: clusters real Langfuse or JSONL traces into a human-confirmed failure taxonomy with counts, then recommends binary pass/fail evals for recurring named modes. Use to learn what to measure before writing evals. Not for CI failures.
examples-qa
Verify Instructor behavior through the repository's ./examples/ suite in pass, live record, or hermetic replay mode. Use when running selected examples or the corpus, capturing and reusing recorded LLM HTTP responses, diagnosing hub results, or distinguishing real errors, assertion failures, skipped examples, and…