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 agentmods add instructions/tyroneross/pyramid-principle/agents-mdgit clone --depth 1 https://github.com/tyroneross/pyramid-principleWrote 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/instructions/tyroneross/pyramid-principle/agents-md)<a href="https://agentmods.dev/instructions/tyroneross/pyramid-principle/agents-md"><img src="https://agentmods.dev/badge/instructions/tyroneross/pyramid-principle/agents-md.svg" alt="Measured on agentmods" 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 | $0.00509 | $0.00509 |
| Opus 5 | $0.00254 | $0.00254 |
| Sonnet 5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
pyramid-principle AGENTS.md 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 6d 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — pyramid-principle
What this plugin is
Barbara Minto's Pyramid Principle plus a separate source-integrity layer, packaged as six composable writing skills. No commands, no agents, no MCP — skills only. Each skill is independently addressable by its skill ID.
How Codex accesses this plugin
.codex-plugin/plugin.json maps the ./skills directory. Skills are auto-loaded on install. Invoke by skill ID (e.g., pyramid-audit).
Skills
| Skill ID | Purpose | Load when |
|---|---|---|
pyramid-source-integrity |
Fact checking, source validation, calculations, data scope, and claim handoff | Load before and after structuring source-bound or data-bearing work |
pyramid-principle-core |
Canonical rule library: SCQA, MECE, deduction/induction, vertical/horizontal logic | Load for every structure or storyline task |
pyramid-short-form |
Draft emails, memos, exec summaries, one-pagers, BLUF notes | Short writing under ~500 words |
pyramid-long-form |
Structure reports, briefs, research writeups, multi-section documents | Multi-section or long-form writing |
pyramid-presentation |
Deck storyline, slide headline hierarchy, data stories | Presentation / slide structure |
pyramid-audit |
Diagnose existing writing against pyramid rules; rule-by-rule findings + fixes | Auditing or critiquing existing content |
Composition
pyramid-principle-core owns the parent writing rules: answer-first structure, valid grouping, specific nouns, active verbs, evidence-led wording, key-term continuity, and logical sentence flow. Use it with one format skill for ordinary writing. Add pyramid-source-integrity when the task requires fact checking, material data, strict source control, or consequential factual output. Its light check gives every data point a specific source and locator, confidence level, and reason; confidence directly determines how the writer treats the point. Use optional strict trace mode for closed source sets, audit-ready or high-risk work, conflicting sources, or separate verification around a smaller model. Strict mode adds claim IDs and a source register, not a redundant permitted-use field. Use deterministic tools for material calculations. docs/source-anchors.md grounds the Minto framework; it does not verify user-supplied facts.
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.
- 6d ago First seen · 29 lines · 509 tokens per session scan A 01a103b45471
pyramid-principle AGENTS.md is an instructions file published in the GitHub repository tyroneross/pyramid-principle (27 stars, last pushed yesterday), licensed Apache-2.0. It adds 509 tokens to every session, about $0.0025 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.