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 tyroneross/pyramid-principle --skill pyramid-source-integritygit 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/skills/tyroneross/pyramid-principle/pyramid-source-integrity)<a href="https://agentmods.dev/skills/tyroneross/pyramid-principle/pyramid-source-integrity"><img src="https://agentmods.dev/badge/skills/tyroneross/pyramid-principle/pyramid-source-integrity/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/tyroneross/pyramid-principle/pyramid-source-integrity"><img src="https://agentmods.dev/badge/skills/tyroneross/pyramid-principle/pyramid-source-integrity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.01533 |
| Opus 5 | $0.00025 | $0.00766 |
| Sonnet 5 | $0.00010 | $0.00307 |
| Haiku 4.5 | $0.00005 | $0.00153 |
Grade A, and why
pyramid-source-integrity 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 9d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pyramid Source Integrity
Purpose
Check factual content without taking over the writing or storyline. pyramid-principle-core and the format skills own structure and expression.
Use the light check by default. Use strict trace mode only when the task needs an audit-ready claim packet, a closed source set, conflicting sources, a high-risk decision, or separate verification around a smaller drafting model.
Light Check
Run three distinct operations when the artifact materially depends on facts or data:
- Check: Clear each factual claim and derived value before drafting.
- Write: Give the structural skill only the cleared claims and necessary evidence limits.
- Recheck: Compare every factual or evaluative clause, headline, table entry, and number with the cleared claims. Include claims carried by verbs, adjectives, and adverbs. Correct or remove any mismatch.
Keep the check internal unless the user requests a fact-check report or an unresolved evidence gap prevents reliable writing.
For each factual claim or derived value, record only what the writer needs:
- the exact claim;
- its type: supplied fact, derived value, inference, recommendation, or opinion;
- a specific source and exact locator;
High,Medium,Low, orUnverifiedconfidence and a short reason; and- any population, period, geography, unit, denominator, qualifier, or causal limit that the wording must preserve.
Do not create a separate permitted use field. Confidence already determines the drafting action:
| Confidence | Drafting action |
|---|---|
| High | State directly without strengthening the source. |
| Medium | Attribute the source or state the limitation. |
| Low | Keep out of central support; use only as a limitation or verification lead. |
| Unverified | Exclude as fact and name the missing evidence when the gap matters. |
Confidence describes support for the exact claim. It is not a probability or a guarantee. Never invent a numerical confidence score. A user-supplied source that was not independently checked cannot exceed Medium.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 118 lines · 50 tokens per session scan A 635d2a5c9921
pyramid-source-integrity is a skill published in the GitHub repository tyroneross/pyramid-principle (28 stars, last pushed 2d ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,533 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…