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 shawnclybor/clybor-claude-tooling --skill five-whysgit clone --depth 1 https://github.com/shawnclybor/clybor-claude-toolingWrote 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/shawnclybor/clybor-claude-tooling/five-whys)<a href="https://agentmods.dev/skills/shawnclybor/clybor-claude-tooling/five-whys"><img src="https://agentmods.dev/badge/skills/shawnclybor/clybor-claude-tooling/five-whys/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/shawnclybor/clybor-claude-tooling/five-whys"><img src="https://agentmods.dev/badge/skills/shawnclybor/clybor-claude-tooling/five-whys.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 | $0.00148 | $0.03423 |
| Opus 5.5 | $0.00059 | $0.01369 |
| Sonnet 5.5 | $0.00030 | $0.00685 |
| Haiku 4.5 | $0.00015 | $0.00342 |
Grade A, and why
five-whys 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 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.
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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Five Whys — Root Cause Analysis
When something breaks and the cause isn't obvious, walk through this protocol before retrying or working around the problem.
Why this matters: blind retries are the #1 source of wasted time and compounding errors. A wrong guess can corrupt data, send to the wrong destination, or overwrite files with stale state. Five minutes of root-cause analysis now saves thirty minutes of cleanup later.
What this protocol produces
A verdict. Not a governance update.
Diagnosis ends when you can name what happened and how well you know it. What to do about it is a separate decision, made after the verdict, from the verdict. Six verdicts are legal (Step 4). Writing a rule is one possible consequence of one of them.
Why this is stated first. An earlier version of this skill ended "Every Five Whys should end with a governance update." That single line corrupted the diagnosis upstream of itself. If the only legal ending is a rule, the search stops at the first cause that can be written as a rule, not at the true cause. Causes that aren't rule-shaped have nowhere to go, so the protocol pressures you to reframe them until they are.
When to invoke
- A tool call fails twice with the same or similar error (Two Strikes Rule)
- A service returns unexpected/wrong data (stale, empty, mis-routed)
- A workflow produces incorrect output despite correct-looking inputs
- The user reports something broke that previously worked
- You catch yourself about to retry something that already failed twice
The Protocol
Step 1 — State the problem, and get the input before diagnosing the output
Write one sentence: what happened vs. what was expected. Be specific. Include the tool name, the exact input, and the actual output.
A vague problem statement ("the X thing broke") leads to a vague investigation. Specificity narrows the search space immediately.
HARD GATE — no input, no root-cause claim
You must have the actual input that produced the failure. Not a reconstruction of it. Not an inference from the error text. The real thing.
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 Changed · +32 lines 019b8f55aaa2
- 1mo ago Changed · +73 lines · +33 tokens per session 0a7083e00275
- 2mo ago First seen · 84 lines · 115 tokens per session scan A 8b6c5bc276b8
five-whys is a skill published in the GitHub repository shawnclybor/clybor-claude-tooling (6 stars, last pushed yesterday), licensed MIT. It adds 148 tokens to every session and 3,423 once invoked, about $0.0006 per session on Opus 5.5. 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.
five-whys compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| five-whysshawnclybor/clybor-claude-tooling | Skill | 6 | yesterday | MIT | A | 148 | Claude Code |
| debugSienkLogic/plan-build-run | Skill | 18 | 7mo ago | MIT | A | 13 | Claude Code |
| scanSienkLogic/plan-build-run | Skill | 18 | 7mo ago | MIT | A | 18 | Claude Code |
| audit-fixSienkLogic/plan-build-run | Skill | 18 | 7mo ago | MIT | A | 22 | Claude Code |
| healthSienkLogic/plan-build-run | Skill | 18 | 7mo ago | MIT | A | 13 | Claude Code |
| forensicsSienkLogic/plan-build-run | Skill | 18 | 7mo ago | MIT | A | 23 | Claude Code |
| yd-finguardLeeYudok/agents-scaffold | Skill | 38 | yesterday | MIT | A | 63 | Claude Code |