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 ConrayGambit/Strategy-Consultant-5-Consulting-Frameworks --skill five-whysgit clone --depth 1 https://github.com/ConrayGambit/Strategy-Consultant-5-Consulting-FrameworksWrote 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/conraygambit/strategy-consultant-5-consulting-frameworks/five-whys)<a href="https://agentmods.dev/skills/conraygambit/strategy-consultant-5-consulting-frameworks/five-whys"><img src="https://agentmods.dev/badge/skills/conraygambit/strategy-consultant-5-consulting-frameworks/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/conraygambit/strategy-consultant-5-consulting-frameworks/five-whys"><img src="https://agentmods.dev/badge/skills/conraygambit/strategy-consultant-5-consulting-frameworks/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 | $0.00072 | $0.01166 |
| Opus 5 | $0.00036 | $0.00583 |
| Sonnet 5 | $0.00014 | $0.00233 |
| Haiku 4.5 | $0.00007 | $0.00117 |
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 12d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
5 Whys
Concept
Toyota's Sakichi Toyoda popularized the 5 Whys: take any apparent cause and ask "Why?" five times in succession. Each answer becomes the new statement; you drill until you hit a root cause that isn't itself a symptom of something deeper.
In the consulting toolkit, 5 Whys complements issue trees. Issue trees go wide (every plausible cause). 5 Whys goes deep on one branch — the one you suspect dominates. It's especially useful after a Pareto step has named the vital 20%, before committing to interventions.
Five is a heuristic, not a magic number. Sometimes you reach root cause at three; sometimes you have to push to seven. The discipline is asking "why" until the answer stops being a symptom and starts being something structural.
Required output format
A numbered list of five Why → Because pairs, followed by a one-sentence root-cause statement.
**Starting problem:** [The apparent issue you're drilling into.]
1. **Why?** [First-level reason]
2. **Why?** [Second-level — drilling into #1's answer]
3. **Why?** [Third-level — drilling into #2's answer]
4. **Why?** [Fourth-level — drilling into #3's answer]
5. **Why?** [Fifth-level — drilling into #4's answer]
**Root cause:** [One-sentence structural cause, addressable as a system change.]
Defaults & flex points
| Default | When to flex |
|---|---|
| 5 levels deep | Sometimes 3 is enough (the structural cause is shallow); sometimes 6–7 is needed (deep institutional cause). Push until the answer is no longer a symptom. |
| One thread | Drill a single chain — don't branch mid-way. If the answer to a "Why?" is multi-causal, pick the dominant cause and drill that one. Run a separate 5 Whys on the other if needed. |
| Each Why builds on the previous | Don't restart the chain or re-ask the same question. Each answer must logically follow from the one above. |
The root-cause test: the final answer should be something you can change as a system — a process, a policy, an incentive, a data-flow design. If the final answer is "people are bad" or "the world is hard," you haven't reached root cause. Push deeper.
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.
- 12d ago First seen · 71 lines · 72 tokens per session scan A 9eb6e0f6e008
five-whys is a skill published in the GitHub repository ConrayGambit/Strategy-Consultant-5-Consulting-Frameworks (23 stars, last pushed 3mo ago), licensed MIT. It adds 72 tokens to every session and 1,166 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
thinking-scientific-method
When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.
thinking-five-whys-plus
When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.
thinking-map-territory
When a claim, doc, test, metric, or assumption conflicts with observed behavior, stop theorizing from the map and verify the live code or data; let territory overrule.
performance-profiling
Guide performance profiling with Instruments, diagnose hangs, memory issues, slow launches, and energy drain. Use when reviewing app performance or investigating specific bottlenecks.
swiftui-debugging
Diagnose SwiftUI performance issues including unnecessary re-renders, view identity problems, and slow body evaluations. Use when SwiftUI views are slow, janky, or re-rendering too often.
debug-menu
Generates a developer debug menu with feature flag toggles, environment switching, network log viewer, cache clearing, crash trigger, and diagnostic info export. Only included in DEBUG builds. Use when user wants a debug panel, dev tools menu, or shake-to-debug functionality.