Borrowing it
Nothing to install: this file belongs to tyroneross/pyramid-principle. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tyroneross/pyramid-principle/main/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/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/instructions/tyroneross/pyramid-principle/agents-md"><img src="https://agentmods.dev/badge/instructions/tyroneross/pyramid-principle/agents-md.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 | $0.00637 | $0.00637 |
| Opus 5.5 | $0.00255 | $0.00255 |
| Sonnet 5.5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00064 | $0.00064 |
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 1mo 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 — 33 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 and an optional local HTML writing workspace. Each skill is independently addressable by its skill ID. The workspace uses a local Node server; it adds no agents or MCP server.
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.
- 1mo ago Changed · +4 lines · +128 tokens per session a0082eddfcb7
- 2mo 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 (43 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 637 tokens to every session, about $0.0025 per session on Opus 5.5. 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.
pyramid-principle AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pyramid-principle AGENTS.mdtyroneross/pyramid-principle | Instructions file | 43 | 1mo ago | Apache-2.0 | A | 637 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |