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 vasanthsreeram/Alvarmethod --skill learn-verifygit clone --depth 1 https://github.com/vasanthsreeram/AlvarmethodWrote 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/vasanthsreeram/alvarmethod/learn-verify)<a href="https://agentmods.dev/skills/vasanthsreeram/alvarmethod/learn-verify"><img src="https://agentmods.dev/badge/skills/vasanthsreeram/alvarmethod/learn-verify/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/vasanthsreeram/alvarmethod/learn-verify"><img src="https://agentmods.dev/badge/skills/vasanthsreeram/alvarmethod/learn-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00074 | $0.00460 |
| Opus 5 | $0.00037 | $0.00230 |
| Sonnet 5 | $0.00015 | $0.00092 |
| Haiku 4.5 | $0.00007 | $0.00046 |
Grade A, and why
learn-verify 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 12d 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.
What it actually says
Learn verify
Trust is engineered. Check the claim before it is taught as fact.
When to run
- Empirical, historical, bibliographic, or API/tool claims
- Named theorems, identities, or "standard facts" you cannot reconstruct
- Anything you were about to present with unearned certainty
Skip a full search only when you can derive the statement in-session and the learner does not need an external citation. Still say that it was derived, not sourced.
Method
- Write the claim in one falsifiable sentence.
- Fetch or search primary-ish sources (paper, textbook, official docs, standard reference). Do not cite a URL you did not open.
- Quote or paraphrase the supporting line. Note edition / year if it matters.
- Mark disagreements. Prefer the source the field actually uses.
- Return a verdict.
Verdict
## Claim
…
## Verdict
confirmed | qualified | contradicted | unknown
## Sources
- <title> — <url or citation> — <what it says>
## Teach as
<one sentence the teacher may now say, with any hedge>
qualified = true under stated assumptions (dimension, characteristic, gauge, version).
unknown = do not teach it as fact. Say you could not verify.
Rules
- No invented papers, quotes, or page numbers.
- One claim per run. Batch only if they are the same fact in different words.
- Write the verdict into the session file if a teach session is open.
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.
- 12d ago First seen · 60 lines · 74 tokens per session scan A d8ebb3595d61
learn-verify is a skill published in the GitHub repository vasanthsreeram/Alvarmethod (152 stars, last pushed 26d ago), licensed MIT. It adds 74 tokens to every session and 460 once invoked, about $0.0004 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.