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/juan294/cc-rpi/systematic-debuggingnpx skills add juan294/cc-rpi --skill systematic-debugginggit clone --depth 1 https://github.com/juan294/cc-rpiWhat 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 | $0.00051 | $0.00660 |
| Opus 5 | $0.00026 | $0.00330 |
| Sonnet 5 | $0.00010 | $0.00132 |
| Haiku 4.5 | $0.00005 | $0.00066 |
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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging
When stuck, stop guessing. Run the loop. Random edits that "might fix it" waste turns and mask the real cause. For known tool/git/CI failures, check the Error Patterns skill first — this skill is for novel bugs.
The Loop
- Reproduce. Get a reliable, minimal repro before changing anything. A bug you cannot reproduce on demand, you cannot confirm fixed. Note the exact command, inputs, and expected-vs-actual.
- Isolate. Shrink the surface. Remove inputs, comment out code, halve the
data until the smallest thing that still fails remains.
git bisectwhen a regression has a known-good past commit. - Hypothesize. State ONE specific, falsifiable cause: "X is null because Y runs before Z." If you cannot name a mechanism, you are still guessing.
- Test the hypothesis. Add a log/breakpoint/assertion that the hypothesis predicts. Observe. Confirm or kill it before touching the fix.
- Fix the root cause. Not the symptom. If the fix is "add a null check," ask why it is null — that is usually the real bug.
- Verify. Re-run the repro from step 1. Then run the surrounding tests to confirm you broke nothing. A fix unconfirmed against the original repro is not a fix.
Discipline
- Read the actual error. Full message, full stack trace, top to bottom. The answer is in there more often than not. Don't skim to the first familiar line.
- One change at a time. Change-everything-and-pray destroys the signal about what actually mattered. Revert failed experiments before the next one.
- Trust nothing, verify everything. Don't assume which function runs, what a variable holds, or that a dependency is installed. Add the log and look.
- Bisect over speculation. When a thing used to work, the diff that broke it is findable mechanically. Don't theorize about a regression you can bisect.
- Question the assumption, not just the code. If reality contradicts your mental model, the model is wrong. Find which assumption is false.
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 · 52 lines · 51 tokens per session scan A a3beeeef2591
systematic-debugging is a skill published in the GitHub repository juan294/cc-rpi (5 stars, last pushed 13d ago), licensed MIT. It adds 51 tokens to every session and 660 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
claude-md-review
Audit a CLAUDE.md file for the patterns that actually degrade Claude Code's output — vagueness, unnamed files, stale facts, and bloat. Use when asked to review, audit, improve, shrink, or fix a CLAUDE.md, and when a project's results feel inconsistent or Claude keeps rediscovering the same context.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).
common-exploit-verification
Enforce "No Exploit, No Report" policy with PoC construction standards, false-positive filtering, and evidence collection per vulnerability class across backend, frontend, and mobile. Use when validating security findings, constructing exploit proofs, filtering false positives, or writing pentest findings.
JavaScript Tooling
Development tools, linting, and testing for JavaScript projects.
common-product-requirements
Standardize PRD discovery and drafting for product scope, user outcomes, requirement IDs, and acceptance criteria. Use when creating PRD, product requirements, feature specification, or acceptance criteria plan.
common-security-audit
Probe for hardcoded secrets, injection surfaces, unguarded routes, business logic flaws, and platform-specific weaknesses across backend (Node, Go, Java, Python, Rust), frontend (React, Angular, Vue), and mobile (iOS, Android, Flutter) codebases. Use when performing security audits, vulnerability scans, secrets…