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 agentmods add skills/clubpay/ronykit/systematic-debuggingnpx skills add clubpay/ronykit --skill systematic-debugginggit clone --depth 1 https://github.com/clubpay/ronykitWhat 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 | $0.00041 | $0.00500 |
| Opus 5 | $0.00020 | $0.00250 |
| Sonnet 5 | $0.00008 | $0.00100 |
| Haiku 4.5 | $0.00004 | $0.00050 |
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 2d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging
Guessing creates new bugs and hides old ones. Find the root cause first.
The iron rule
No fix without a root-cause hypothesis you have confirmed with evidence.
If you cannot explain why the bug happens, you are not ready to fix it.
When to use
Any test failure, crash, wrong output, flaky test, performance regression, build failure, or integration issue — especially when under time pressure or when a previous fix didn't hold.
Phase 1 — Understand
- Read the full error and stack trace; note file, line, and exact message.
- Reproduce it reliably. A bug you can't reproduce, you can't verify fixed.
- Establish the smallest reproduction and the expected vs actual behavior.
Phase 2 — Investigate
- Form a hypothesis about the cause and predict what you'd observe if true.
- Gather evidence: targeted logging, a debugger,
git bisect, binary search by commenting/disabling, or diffing a working vs broken state. - Follow the data flow backward from the symptom to its origin. Question assumptions ("this can't be nil" — prove it).
Phase 3 — Fix the cause
- Change the root cause, not the symptom. Patching where it crashed instead of where the bad value originated just moves the bug.
- Make the smallest change that addresses the cause.
Phase 4 — Verify & prevent
- Write a test that fails before the fix and passes after.
- Re-run the full relevant suite to check for regressions.
- Ask whether the same class of bug exists elsewhere.
Tactics
git bisectto locate the introducing commit.- Binary search the input/code path to isolate the trigger.
- Add structured logging at decision points; remove it before committing.
- For flakiness: suspect time, ordering, concurrency, and shared state; run with
-race/ repeated runs.
Anti-patterns
- Trying random changes to see what sticks.
- Adding defensive
if x == nilguards without knowing whyxis nil. - Declaring it fixed because the symptom disappeared once.
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.
- 2d ago First seen · 64 lines · 41 tokens per session scan A 1f5380c6e817
systematic-debugging is a skill published in the GitHub repository clubpay/ronykit (38 stars, last pushed 4d ago), licensed BSD-3-Clause. It adds 41 tokens to every session and 500 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 2026-08-30.
Other skills, from other repositories
sql-database-support
Guides classifying, gap-analyzing, and scaffolding support for a new SQL database in pREST (wire-compatible variants like TimescaleDB or new dialects). Use when adding database support, creating integration/ /, DIFFERENCES.md, adapters/ , per-DB docker-compose or GitHub workflows, or planning where config/app wiring…
prest-integration-tests
Guides writing and reviewing pREST Docker/network integration tests under integration/ so each request is human-readable via step comments or table-driven descriptions. Use when adding or editing integration//test.go, HTTP controller E2E coverage, make test-integration, test-integration-postgres…
ast-introspection
Use Go AST-aware analysis to enumerate symbols, extract signatures, and propose mechanically safe refactors (read-only by default).
ci-orchestrator
Run a CI-like pipeline locally (format, lint, vet, static-analysis, tests) and summarize per-step results with remediation guidance.
config-loader-helper
Diagnose configuration-related failures, enumerate required env vars, and guide safe local test setup (no secrets).
db-infra-mocks
Propose minimal seams and local substitutes so tests run without real RDBMS/Redis/Mongo infrastructure.