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 HirogaKatageri/hirokata --skill pyramid-principlegit clone --depth 1 https://github.com/HirogaKatageri/hirokataWrote 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/hirogakatageri/hirokata/pyramid-principle)<a href="https://agentmods.dev/skills/hirogakatageri/hirokata/pyramid-principle"><img src="https://agentmods.dev/badge/skills/hirogakatageri/hirokata/pyramid-principle/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/hirogakatageri/hirokata/pyramid-principle"><img src="https://agentmods.dev/badge/skills/hirogakatageri/hirokata/pyramid-principle.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 | $0.00120 | $0.01252 |
| Opus 5 | $0.00060 | $0.00626 |
| Sonnet 5 | $0.00024 | $0.00250 |
| Haiku 4.5 | $0.00012 | $0.00125 |
Grade A, and why
pyramid-principle 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 11d 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.
Pyramid Principle — Lead With the Answer
Barbara Minto (McKinsey). Busy decision-makers don't want your reasoning journey — they want the conclusion, then the support if they choose to dig. So invert the natural order: state the answer first, then the grouped arguments, then the data underneath. Ideas form a pyramid where every level summarizes the level below.
┌──────────────────────────┐
│ GOVERNING THOUGHT │ the answer / recommendation
└──────────────────────────┘
╱ │ ╲
┌──────────┐ ┌──────────┐ ┌──────────┐
│ Argument │ │ Argument │ │ Argument │ 3–5, MECE
└──────────┘ └──────────┘ └──────────┘
│ │ │ │ │ │ │ │ │
data data data data data data evidence
The Structure
- Governing thought. The single main message — usually a recommendation or answer. One sentence. Everything below exists to support it.
- Key arguments (3–5), MECE. Mutually Exclusive (no overlap) and Collectively Exhaustive (nothing important missing). Each argument is itself a mini-conclusion, not a topic label.
- Evidence. Data, facts, and examples supporting each argument. This is where detail lives — out of the reader's way until they want it.
The SCQA opener (optional but powerful) sets up the governing thought in a way the reader already agrees with:
- Situation — the stable context everyone accepts.
- Complication — what changed or went wrong that demands a response.
- Question — the question the complication raises (often implicit).
- Answer — your governing thought. Then the pyramid unfolds beneath it.
When to use it (and when not)
Use it for: board and exec presentations, investor updates, decision and recommendation memos, strategy docs, executive summaries, any "we need a yes/no" moment.
Reach for something else when: you want to inspire or set a vision (→ golden-circle), you're
telling a transformation story (→ pixar-pitch), or you need a 30-second hook (→ abt). The
Pyramid is for clarity and decisions, not for emotion.
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.
- 11d ago First seen · 100 lines · 120 tokens per session scan A 9e69a20e47ab
pyramid-principle is a skill published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed 2d ago), licensed MIT. It adds 120 tokens to every session and 1,252 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
unslop
Humanize LLM output so it reads like a careful human wrote it. Subtracts AI-isms (sycophancy, tricolons, em-dash overuse, "delve"/"tapestry"/"testament", hedging stacks, tidy five-paragraph shapes), engineers burstiness and calibrated uncertainty, and preserves technical accuracy. Supports intensity levels: subtle…
unslop-file
Humanize natural-language memory files (CLAUDE.md, todos, preferences, docs) by removing AI-isms and adding burstiness while preserving every code block, URL, path, command, and heading exactly. Two modes: --deterministic (fast, regex-based, no API) and LLM (default, calls Claude for rewrite). Humanized version…
unslop-commit
Rewrites commit messages so they sound like a careful human engineer wrote them. Strips AI/marketing slop ("comprehensive solution", "robust implementation", "leverage", "enhance", "seamlessly", "This commit..."). Keeps Conventional Commits format. Subject ≤72 chars (aim ≤50), imperative mood. Body only when "why"…
unslop-help
Quick-reference card for unslop modes, sub-skills, and slash commands. One-shot display, not a persistent mode. Trigger: /unslop-help, "unslop help", "what unslop commands", "how do I use unslop".
simulator-charts
Simulator.Company chart and dashboard specialist. Use when the user wants to create, configure, or query charts (line, bar, area), dashboards, or financial time-series visualisations on a graph layer. Trigger on any of these intents: — Creating: "create chart", "add chart", "create dashboard", "add dashboard", "build…
simulator-init
Simulator.Company environment setup specialist. Use when the user wants to connect to Simulator.Company, set up credentials, authenticate, configure the workspace, or start working with Simulator for the first time. Activate when the user says "init", "setup", "connect to simulator", "login to simulator", "configure…