diagnosing-bugs

A structured method for finding the cause of difficult software bugs, failures, and slowdowns.

In plain words
What is it for?
It helps investigate broken behavior, thrown errors, and performance regressions while examining the relevant code and project decisions.
Why use it?
It replaces guesswork with a repeatable feedback loop, such as a failing test or another clear check that shows whether a suspected fix works.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/docs-plus/docs.plus/diagnosing-bugs
Any agent
npx skills add docs-plus/docs.plus --skill diagnosing-bugs
Clone the repo
git clone --depth 1 https://github.com/docs-plus/docs.plus

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,081 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin 92% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.02081
Opus 5 $0.00020 $0.01040
Sonnet 5 $0.00008 $0.00416
Haiku 4.5 $0.00004 $0.00208

Measured 2d ago against content hash b9339b09ee39, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

diagnosing-bugs scanned grade A with 1 finding 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/hitl-loop.template.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Phase 1 is done when the loop is **tight** and **red-capable**: you can name **one command** — a script path, a test invocation, a curl — that you have **already run at least once** (show the invocation and its output, r
Origin

This is a copy

92% identical to diagnosing-bugs — 58 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.

.agents/skills/diagnosing-bugs/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diagnosing Bugs

A discipline for hard bugs. Skip phases only when explicitly justified.

When exploring the codebase, read CONTEXT.md (if it exists) to get a clear mental model of the relevant modules, and check ADRs in the area you're touching.

Redact

This skill has you show commands, outputs and captured artifacts. Redact every secret first — write <REDACTED> in its place. Build loops against env vars, so the credential stays in the environment rather than in what you show. Captured artifacts carry auth headers: quote only the lines that carry the signal.

If the redacted output is not enough to diagnose the bug, say so and ask the user.

Phase 1 — Build a feedback loop

This is the skill. Everything else is mechanical. If you have a tight pass/fail signal for the bug — one that goes red on this bug — you will find the cause; bisection, hypothesis-testing, and instrumentation all just consume it. If you don't have one, no amount of staring at code will save you.

Spend disproportionate effort here. Be aggressive. Be creative. Refuse to give up.

Ways to construct one — try them in roughly this order

  1. Failing test at whatever seam reaches the bug — unit, integration, e2e.
  2. Curl / HTTP script against a running dev server.
  3. CLI invocation with a fixture input, diffing stdout against a known-good snapshot.
  4. Headless browser script (Playwright / Puppeteer) — drives the UI, asserts on DOM/console/network.
  5. Replay a captured trace. Save a real network request / payload / event log to disk; replay it through the code path in isolation.
  6. Throwaway harness. Spin up a minimal subset of the system (one service, mocked deps) that exercises the bug code path with a single function call.
  7. Property / fuzz loop. If the bug is "sometimes wrong output", run 1000 random inputs and look for the failure mode.
  8. Bisection harness. If the bug appeared between two known states (commit, dataset, version), automate "boot at state X, check, repeat" so you can git bisect run it.
  9. Differential loop. Run the same input through old-version vs new-version (or two configs) and diff outputs.
  10. HITL bash script. Last resort. If a human must click, drive them with scripts/hitl-loop.template.sh so the loop is still structured. Captured output feeds back to you.

Read the full file on GitHub · 141 lines

Files

What ships with it

2 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.

Changes

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.

  1. 2d ago First seen · 141 lines · 40 tokens per session scan A b9339b09ee39

Subscribe to this mod's changes

diagnosing-bugs is a skill published in the GitHub repository docs-plus/docs.plus (88 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 2,081 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 92% identical to diagnosing-bugs, differing in 58 lines, and is treated as a copy.

Related

Other skills, from other repositories

docx

Read, create, and convert Microsoft Word (.docx) documents — extract text and tables, build reports from markdown/JSON, and export to PDF.

zhixuli0406/DuDuClaw · 34 tokens

document-converter

Convert Office documents (PPTX, DOCX, XLSX, PDF, HTML, CSV, JSON, XML, images) to Markdown using Microsoft MarkItDown. Provides the agent with conversion strategies for academic and research workflows.

wentorai/Research-Claw · 50 tokens

docx-manipulation

Create, edit, and manipulate Word documents programmatically using python-docx.

claude-office-skills/skills · 20 tokens

add-format

End-to-end checklist for adding a new input or output format to AILANG Parse (docparse). Use when the user says 'add support for X format', 'wire up a new parser', 'add .foo format', 'add a parser for .bar', 'support .baz files', 'ship format X', 'can we parse .qux', 'new format rollout', or mentions a file extension…

sunholo-data/ailang-parse · 183 tokens

landing-page

Create a new AILANG Parse documentation/landing page targeting a specific keyword or topic. Use when user says 'new landing page', 'new page for X', 'create a page about X', 'landing page for keyword X', or wants to add a documentation page to the docs/ site. Also use when the user references long-tail keywords, SEO…

sunholo-data/ailang-parse · 81 tokens

benchmark

Run OfficeDocBench evaluation and refresh benchmark scores across the AILANG Parse website. Use when the user says 'run benchmarks', 'rerun the benchmark', 'refresh benchmark numbers', 'update bench scores', 'regenerate summary.json', mentions OfficeDocBench, asks to evaluate parsers, asks why scores are out of sync…

sunholo-data/ailang-parse · 115 tokens