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 ralfyishere/rules-with-receipts --skill debugging-playbookgit clone --depth 1 https://github.com/ralfyishere/rules-with-receiptsWrote 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/ralfyishere/rules-with-receipts/debugging-playbook)<a href="https://agentmods.dev/skills/ralfyishere/rules-with-receipts/debugging-playbook"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/debugging-playbook.svg" alt="Measured on agentmods" 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 | $0.00099 | $0.01675 |
| Opus 5 | $0.00049 | $0.00838 |
| Sonnet 5 | $0.00020 | $0.00335 |
| Haiku 4.5 | $0.00010 | $0.00168 |
Grade A, and why
Debugging Playbook 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 7d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugging Playbook
Purpose
Replace guess-and-check with evidence-and-elimination. Unstructured debugging is a random walk: plausible fixes applied to unconfirmed causes, each failed attempt polluting the state for the next. The playbook's core rule: you have found the root cause when you can predict the system's behavior — before and after the fix — and be right.
When to use this skill
- Anything broken, failing, or surprising: errors, test failures, wrong output, crashes, hangs, performance drops.
- "It worked before" situations — these are diffing problems in disguise.
- Non-code failures with the same shape: a spreadsheet total that's off, a pipeline producing bad rows, a prompt whose outputs degraded.
- Intermittent problems — especially these; guessing is uniquely useless against nondeterminism.
When NOT to use this skill
- The cause is already proven and trivial (the error message names the missing import). Fix it; ceremony adds nothing.
- Nothing is broken — for "could this break?" work, use
failure-mode-awareness. - Building new things — that's
plan-gate/deep-decompositionterritory, even if motivated by a bug.
Operating procedure
1 — Capture the symptom, verbatim. Full error text, exact command, exact input, environment. "Something about a timeout" is not a symptom. Note what correct behavior would look like — surprising numbers of debugging sessions chase behavior that was actually fine.
2 — Reproduce it. Find the smallest, fastest, most deterministic reproduction you can. Every minute invested here is repaid at every hypothesis test. If you cannot reproduce: don't guess-fix — instrument (logging, counters, capture-on-failure) and wait for the next occurrence, or hunt for the missing trigger condition (timing, data, environment).
- For "worked yesterday": diff the worlds. What changed between then and now — code, data, dependencies, config, environment?
git log/ deploy history / dependency lockfile first.
3 — Generate 2–4 ranked hypotheses. Rank by likelihood × cheapness-to-test. Sources: the error itself (read all of it), the diff since it last worked, the failure catalogs in failure-mode-awareness, and where this class of bug usually lives.
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.
- 7d ago First seen · 82 lines · 0 tokens per session scan A 8508668aa8e5
Debugging Playbook is a skill published in the GitHub repository ralfyishere/rules-with-receipts (2 stars, last pushed 1mo ago), licensed MIT. It adds 99 tokens to every session and 1,675 once invoked, about $0.0005 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
code-review
Reviews code for bugs, security issues, and best practices.
error-translator
A Chinese-language assistant that translates English programming errors and explains what they mean. It covers common errors from languages and frameworks including Python, JavaScript, TypeScript, Java, and others.
eslint-fix
A project-aware assistant for finding and fixing ESLint errors, warnings, and configuration compatibility problems. ESLint is a tool that checks JavaScript and TypeScript code for style and common mistakes.
perf-profiler
A performance investigation guide that uses repeatable measurements and profiling evidence to find where software spends time or resources. Profiling records runtime activity such as CPU use, memory use, database work, or network delays.
log-analyzer
A log-analysis helper that reads application and system logs to find unusual patterns and likely causes. Logs are records of events such as errors, requests, warnings, and service activity.
bug-reproducer
Find likely software bugs in a codebase, rank concrete bug candidates, and prove or reject them with focused regression tests before proposing a fix. Also turn bug reports, stack traces, screenshots, failing behavior, support tickets, and regressions into minimal reproducible cases with red-to-green evidence. Use when…