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 issue-treesgit 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/issue-trees)<a href="https://agentmods.dev/skills/conraygambit/strategy-consultant-5-consulting-frameworks/issue-trees"><img src="https://agentmods.dev/badge/skills/conraygambit/strategy-consultant-5-consulting-frameworks/issue-trees/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/issue-trees"><img src="https://agentmods.dev/badge/skills/conraygambit/strategy-consultant-5-consulting-frameworks/issue-trees.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 | $0.00058 | $0.00973 |
| Opus 5 | $0.00029 | $0.00487 |
| Sonnet 5 | $0.00012 | $0.00195 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
issue-trees 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 10d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue Trees
Concept
An issue tree breaks a vague problem into progressively smaller, more concrete sub-problems until you reach something testable. Each branch is a hypothesis about why the parent problem exists. Done well, the leaves are things you can actually go investigate.
Required output format
A fenced code block with text syntax. Use ASCII box-drawing characters:
├──non-final child│vertical continuation under a non-final child└──final child at each level
```text
Core Problem
├── Category 1
│ ├── Sub-factor A
│ └── Sub-factor B
└── Category 2
└── Sub-factor C
```
Rendering fallback
Some destinations mangle box-drawing characters — Slack, certain email clients, and some chat UIs render them as boxes or question marks. If you know the output is heading to one of those, use an indented-dash tree instead:
- Core Problem
- Category 1
- Sub-factor A
- Sub-factor B
- Category 2
- Sub-factor C
It loses some elegance but stays readable everywhere. Default to box-drawing; switch only when needed.
This is "Slack mode." When the user asks for Slack / Teams / email / plain-text output (or names that as the destination), use this indented-dash form for the whole tree by default.
Defaults & flex points
| Default | When to flex |
|---|---|
| At least 2 levels deep | A 1-level tree is a list. Push deeper. For complex problems, 3–4 levels. |
| 3–8 words per node | Stay short — long node text destroys readability. |
| Branches MECE at each level | This one doesn't flex. |
| Stop when leaves are testable | A leaf that says "we have problems with customers" isn't done. "Onboarding completion fell to 61%" is. |
Example — marketing / conversion
Problem: E-commerce site conversion rate dropped from 3.2% to 1.9% over Q3.
Conversion 3.2% → 1.9%
├── Traffic mix shift
│ ├── Paid social spend redirected to top-of-funnel
│ ├── Branded search share fell
│ └── Affiliate program reduction
├── On-site experience
│ ├── Page-load time +800ms after CDN change
│ ├── New checkout layout shipped Aug 14
│ └── Mobile bounce rate climbing
├── Pricing & promotion
│ ├── Promo cadence reduced (cost-cutting)
│ ├── Free-shipping threshold raised $50 → $75
│ └── Competitor undercutting on top 20 SKUs
└── Inventory & merchandising
├── 12 hero SKUs out of stock
├── New collection launch delayed two weeks
└── Recommendation algorithm retrained
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.
- 10d ago First seen · 100 lines · 58 tokens per session scan A 03b9f6b6e92a
issue-trees is a skill published in the GitHub repository ConrayGambit/Strategy-Consultant-5-Consulting-Frameworks (23 stars, last pushed 3mo ago), licensed MIT. It adds 58 tokens to every session and 973 once invoked, about $0.0003 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-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-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-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.
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.
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.
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.