diagnose-hard-problem

diagnose-hard-problem is a skill for Claude Code, Codex from sammcj/agentic-coding. It costs 37 tokens per session (2,101 once invoked), scanned A, a copy of diagnosing-bugs, Apache-2.0.

A step-by-step method for investigating difficult bugs and regressions, which are problems introduced by a change. It works by reproducing the problem, narrowing it down, testing explanations, fixing it, and adding a regression test.

In plain words
What is it for?
Diagnosing persistent bugs, isolating the smallest failing case, examining evidence, testing hypotheses, and verifying fixes with tests.
Why use it?
It replaces guesswork with a repeatable investigation loop and helps prevent the same failure from returning.

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/sammcj/agentic-coding/diagnose-hard-problem
Any agent
npx skills add sammcj/agentic-coding --skill diagnose-hard-problem
Clone the repo
git clone --depth 1 https://github.com/sammcj/agentic-coding

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for diagnose-hard-problem

README.md
[![agentmods](https://agentmods.dev/badge/skills/sammcj/agentic-coding/diagnose-hard-problem.svg)](https://agentmods.dev/skills/sammcj/agentic-coding/diagnose-hard-problem)
Your own site
<a href="https://agentmods.dev/skills/sammcj/agentic-coding/diagnose-hard-problem"><img src="https://agentmods.dev/badge/skills/sammcj/agentic-coding/diagnose-hard-problem.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,101 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin 83% 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 $0.00037 $0.02101
Opus 5 $0.00018 $0.01051
Sonnet 5 $0.00007 $0.00420
Haiku 4.5 $0.00004 $0.00210

Measured yesterday against content hash 6f565736f83a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

diagnose-hard-problem 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 yesterday.

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 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, redacted), and that is:
Origin

This is a copy

83% identical to diagnosing-bugs — 79 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.

Skills_disabled/diagnose-hard-problem/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diagnose

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

When exploring the codebase, use the project's domain glossary to get a clear mental model of the relevant modules, and check ADRs in the area you're touching.

Note: In addition to this skill, you may consider activating the systematic-debugging skill when diagnosing complex, persistent issues.

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 fast, deterministic, agent-runnable pass/fail signal for the bug, you will find the cause - bisection, hypothesis-testing, and instrumentation all just consume that signal. 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 · 146 lines

Files

What ships with it

1 file 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. yesterday First seen · 146 lines · 37 tokens per session scan A 6f565736f83a

Subscribe to this mod's changes

diagnose-hard-problem is a skill published in the GitHub repository sammcj/agentic-coding (159 stars, last pushed yesterday), licensed Apache-2.0. It adds 37 tokens to every session and 2,101 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 83% identical to diagnosing-bugs, differing in 79 lines, and is treated as a copy.

Related

Other skills, from other repositories

ap-policies

Attach a completion policy gate (shell check or judge-agent rubric) to a session or fan-in group so turn-end only passes when the gate is green, then optionally auto-commit pending human ack. Use when the user says "gate this session on tests passing", "attach a policy", "commit only if tests are green", "judge…

agentproto/ts · 83 tokens

tdd-workflow

Test-Driven Development workflow principles. RED-GREEN-REFACTOR cycle.

ashrafmusa/agenticana · 21 tokens

python-testing-patterns

Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.

beel-collab/presets.dev · 33 tokens

strands-review

Local preview of the strands-agents/devtools /strands review agent. Body is the upstream Task Reviewer SOP verbatim — do not paraphrase. Use when the user types /strands-review, asks for a "strands review" of a PR, or wants to anticipate what the remote /strands review GitHub Action will flag. Findings are close but…

strands-agents/harness-sdk · 125 tokens

pr-writer

Generates pull request titles and descriptions. Use when the user asks to create, open, write, draft, or generate a PR, pull request, or merge request description.

strands-agents/harness-sdk · 39 tokens

docs-writer

Draft or rewrite Strands Agents documentation pages. Use when writing new doc pages, rewriting pages that failed audit, drafting sections for existing pages, or writing blog posts and release notes about Strands. Also triggers on "write a doc", "draft a page", "rewrite the quickstart", "add a tutorial for X"…

strands-agents/harness-sdk · 74 tokens