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 agentmods add skills/sammcj/agentic-coding/diagnose-hard-problemnpx skills add sammcj/agentic-coding --skill diagnose-hard-problemgit clone --depth 1 https://github.com/sammcj/agentic-codingWrote 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/sammcj/agentic-coding/diagnose-hard-problem)<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>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 | $0.00037 | $0.02101 |
| Opus 5 | $0.00018 | $0.01051 |
| Sonnet 5 | $0.00007 | $0.00420 |
| Haiku 4.5 | $0.00004 | $0.00210 |
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.
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: 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.
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
- Failing test at whatever seam reaches the bug - unit, integration, e2e.
- Curl / HTTP script against a running dev server.
- CLI invocation with a fixture input, diffing stdout against a known-good snapshot.
- Headless browser script (Playwright / Puppeteer) - drives the UI, asserts on DOM/console/network.
- Replay a captured trace. Save a real network request / payload / event log to disk; replay it through the code path in isolation.
- 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.
- Property / fuzz loop. If the bug is "sometimes wrong output", run 1000 random inputs and look for the failure mode.
- 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 runit. - Differential loop. Run the same input through old-version vs new-version (or two configs) and diff outputs.
- HITL bash script. Last resort. If a human must click, drive them with
scripts/hitl-loop.template.shso the loop is still structured. Captured output feeds back to you.
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.
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.
- yesterday First seen · 146 lines · 37 tokens per session scan A 6f565736f83a
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.
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…
tdd-workflow
Test-Driven Development workflow principles. RED-GREEN-REFACTOR cycle.
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.
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…
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.
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"…