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 steph-dove/klaussy-agents --skill debuggit clone --depth 1 https://github.com/steph-dove/klaussy-agentsWrote 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/steph-dove/klaussy-agents/debug)<a href="https://agentmods.dev/skills/steph-dove/klaussy-agents/debug"><img src="https://agentmods.dev/badge/skills/steph-dove/klaussy-agents/debug.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 | $0.00054 | $0.01438 |
| Opus 5 | $0.00027 | $0.00719 |
| Sonnet 5 | $0.00011 | $0.00288 |
| Haiku 4.5 | $0.00005 | $0.00144 |
Grade A, and why
{{REPO}}-debug 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 4d 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.
This is a copy
95% identical to fastapi-debug — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug the error or issue the user described. Do NOT jump to a fix. Follow these phases in order.
Phase 1: Reproduce and Understand
- Read CLAUDE.md for project structure, test commands, and known pitfalls.
- Read any
.claude/rules/*.mdwhosepaths:glob matches the file(s) where the bug surfaces. Path-scoped rules often encode the conventions a fix needs to respect. - Understand the failure. What exactly is going wrong? Read the error message, stack trace, or described behavior carefully. Identify:
- What is the expected behavior?
- What is the actual behavior?
- When did it start? Run
git log --oneline -10to check for recent changes that could be the cause.
- Reproduce it. If there's a test command or way to trigger the bug, run it now. If you can't reproduce it, say so before proceeding — a fix you can't verify is a guess.
Phase 2: Diagnose
Do NOT write any fix yet. Investigate read-only until you understand the root cause.
- Find the code path. Starting from the error location or the described behavior, trace the execution. The three operations below are independent — issue them as a single batch of parallel tool calls, not sequentially:
- Grep for the error message, function name, or component.
- Read the file where the failure occurs — the full file, not just the function.
- Trace backwards: what calls this code? What data does it receive?
- Find the actual data source. If the bug involves wrong values, read the query or data access that produces them. Do not assume — read the actual code.
- Form 3–5 competing hypotheses for the root cause and rank them by likelihood. Do not anchor on the first plausible explanation — the obvious one is often itself a symptom. For each hypothesis, note what evidence would confirm it and what would kill it.
- Gather runtime evidence — don't conclude from static reading alone. Where practical, add temporary logging, inspect the actual runtime values / server logs, or step through the repro, and see which hypothesis the real data supports. Reading code suggests a cause; runtime behavior confirms it. (Skipping this is the classic failure mode: rewriting logic to fix a guessed cause without ever checking the actual data.)
- Identify the root cause. Ask yourself:
- Is this a logic error, a data error, or a state error?
- Is this a regression from a recent change? Check
git diffandgit log. - Could this be caused by something upstream of where the error appears?
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.
- 4d ago First seen · 94 lines · 0 tokens per session scan A f59012d5ad5a
{{REPO}}-debug is a skill published in the GitHub repository steph-dove/klaussy-agents (16 stars, last pushed 11d ago), licensed MIT. It adds 54 tokens to every session and 1,438 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to fastapi-debug, differing in 3 lines, and is treated as a copy.
Other skills, from other repositories
debugging
Use when debugging bugs, test failures, or unexpected behavior. Triggers: 'why isn't this working', 'this doesn't work', 'X is broken', 'something's wrong', 'getting an error', 'exception in', 'stopped working', 'regression', 'crash', 'hang', 'flaky test', 'intermittent failure', or when user pastes a stack…
ralphctl-debugging-and-error-recovery
Systematic root-cause debugging. Use when tests fail, builds break, or behaviour does not match expectations. Follow stop-the-line → reproduce → localize → reduce → root-cause → guard-with-regression-test → verify, not guessing; the reproduction and regression steps follow the same red-green discipline as…
fix-bug
Investigates and fixes a reported bug. Reads relevant code, identifies the root cause, proposes a fix, and adds or updates tests to prevent regression. Invoked when the user describes unexpected behavior, an error, a crash, or a failing test.
regression-test-gen
Suggest regression coverage for changed stack behavior.
crash-recovery
Autonomous crash recovery procedure - diagnose a crash from captured context, write a failing regression test, apply a minimal fix, verify, and write a post-mortem report. Use when given a phantom crash context or asked to recover from a crash.
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.