Borrowing it
Nothing to install: this file belongs to sagar-shirwalkar/collibra-atlas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sagar-shirwalkar/collibra-atlas/main/.agents/skills/debugging/SKILL.mdgit clone --depth 1 https://github.com/sagar-shirwalkar/collibra-atlasWrote 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/sagar-shirwalkar/collibra-atlas/debugging)<a href="https://agentmods.dev/skills/sagar-shirwalkar/collibra-atlas/debugging"><img src="https://agentmods.dev/badge/skills/sagar-shirwalkar/collibra-atlas/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/sagar-shirwalkar/collibra-atlas/debugging"><img src="https://agentmods.dev/badge/skills/sagar-shirwalkar/collibra-atlas/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 | $0.00047 | $0.01274 |
| Opus 5 | $0.00023 | $0.00637 |
| Sonnet 5 | $0.00009 | $0.00255 |
| Haiku 4.5 | $0.00005 | $0.00127 |
Grade A, and why
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 8d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugging
Tenets
- Reproduce first — A bug you can trigger on demand is a bug you can fix. A bug you cannot reproduce is a guess. Invest in reproduction before anything else.
- One hypothesis at a time — Change one thing, observe the result. Changing two things at once tells you nothing about which one mattered.
- Bias toward evidence — The stack trace tells you where, not why. The actual cause is rarely where the error is raised. Dig upstream.
Leading words
- Probe — A targeted diagnostic (print, log, added assertion, narrowed input) placed at a known point to reveal state. Probes are cheap and disposable; place them aggressively, remove them on fix.
- Bisect — Binary search through the chain of cause and effect: half the commits, half the input, half the code path. Each bisect eliminates half the search space.
- Monomorph — Reduce variability. Pin every variable you can (seed, input, config, environment) so only the suspect remains free. A flaky test is a test you haven't monomorphed.
- Rubber duck — Explain the problem aloud, to an inanimate object or empty buffer. The gap between what you think the code does and what it actually does appears in the telling. Cheap, fast, often sufficient alone.
Phases
PHASE 1: Reproduce
Completion criterion: a reliable, documented reproduction case — the exact command or input, the exact output, and the exact conditions.
- Capture the exact error: full traceback, exit code, unexpected output.
- Check what changed — most bugs are recent. Run
git log --oneline -10in the affected module. Note recent commits, dependency bumps, or config changes that bracket the first appearance of the bug. - Find or create the minimal reproducer — the shortest input and fewest steps that trigger the failure. A test is the ideal reproducer.
- Reproduce at least twice to confirm consistency.
- If the failure is intermittent (flaky), document the pass/fail rate first, then skip to FLAPPING.md.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 79 lines · 47 tokens per session scan A 85c25f91fde3
debugging is a skill published in the GitHub repository sagar-shirwalkar/collibra-atlas (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,274 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 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.