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 jeffreytse/grimoire-core --skill apply-fishbone-diagramgit clone --depth 1 https://github.com/jeffreytse/grimoire-coreWrote 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/jeffreytse/grimoire-core/apply-fishbone-diagram)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-fishbone-diagram"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-fishbone-diagram/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/jeffreytse/grimoire-core/apply-fishbone-diagram"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-fishbone-diagram.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 | $0.00042 | $0.01959 |
| Opus 5 | $0.00021 | $0.00979 |
| Sonnet 5 | $0.00008 | $0.00392 |
| Haiku 4.5 | $0.00004 | $0.00196 |
Grade A, and why
apply-fishbone-diagram 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 8d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Fishbone Diagram
Map all potential causes of a problem across 6 standard categories (Machine, Method, Material, Man, Measurement, Environment) in a visual cause-and-effect diagram — surfacing the full landscape of contributing factors before selecting which root cause to investigate, preventing the premature single-cause fixation that makes problems recur.
Why This Is Best Practice
Adopted by: Standard tool in ISO 9001 quality management systems (adopted by 1M+ certified organizations globally). Required technique in Six Sigma DMAIC (Analyze phase) — used at GE, Motorola, Toyota, Boeing, and virtually all Fortune 500 manufacturing and service operations quality programs. Ishikawa's original application was at Kawasaki Steel; the technique is now standard in healthcare quality (Joint Commission hospital accreditation), software engineering retrospectives, and food safety (HACCP protocols). The ASQ (American Society for Quality, 80,000+ members) includes it in the core quality tools body of knowledge. Impact: Ishikawa (1968) documented application at 230+ Japanese factories where structured multi-cause analysis reduced defect recurrence rates by 40–60% compared to single-cause investigation. Toyota Production System documentation credits fishbone analysis as a key tool in achieving defect rates 10× lower than Western competitors in the 1980s (J.D. Power quality studies). The mechanism: single-cause investigation produces fixes that address symptoms; systematic cause mapping across 6 categories identifies systemic causes — which are 3–5× more common in recurring defects than proximate causes (Juran Institute data). Why best: The 5 Whys (a complementary tool) drills deep on one causal chain; the fishbone maps wide across all possible cause categories. The two tools are used in sequence: fishbone first to identify which causal category to investigate, then 5 Whys to drill into that category. Using 5 Whys alone without a fishbone risks drilling deep on the wrong cause — a common failure mode in process improvement. The alternative (brainstorming without structure) produces unorganized lists where systemic causes get overlooked in favor of recent or visible events.
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.
- 8d ago First seen · 142 lines · 42 tokens per session scan A ef246a093769
apply-fishbone-diagram is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 23d ago), licensed MIT. It adds 42 tokens to every session and 1,959 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
performance-profiling
CPU, memory, network bottleneck analysis — systematic performance investigation.
power-bi-performance-troubleshooting
Systematic Power BI performance troubleshooting prompt for identifying, diagnosing, and resolving performance issues in Power BI models, reports, and queries.
refactor
Systematic code refactoring to improve maintainability without changing behavior. Use when asked to "refactor this", "clean up this code", "improve code quality", "simplify this", "reduce complexity", or "eliminate code smells". Always preserves existing behavior.
extension-audit-methodology
Systematic 5-dimension audit framework for VS Code extensions — debug hygiene, dead code, performance, menu validation, dependency cleanup.
refactoring-patterns
Safe transformations — same behavior, better structure.
universal-audit-pattern
Systematic project audit pattern — version consistency, terminology, fact inventory, cross-references.